The
libs/iris/area: ~262 Nx libraries that make up Iris, Oshun's AI-assistant domain — the conversation engine, agent runtime, knowledge/RAG, four-tier memory, multimodal (voice/vision/BCI/spatial) I/O, emotional intelligence, personalization, privacy/safety, platform tooling, and multi-language SDKs.
What this area is#
Iris is the platform's conversational and agentic AI substrate, and by project
count it is the largest single lib area in the monorepo. It is not one package
but 262 separate Nx libraries under libs/iris/, each scoped scope:iris
(18 tagged scope:shared and 1 tagged scope:oshun) and almost all implemented
in TypeScript. The packages are organised by capability sub-system rather than
as one monolith, so a consumer can pull in only the slice it needs — e.g. just
@iris/conversation-core and one provider, or the full agent + tools +
computer-use stack.
The area layers roughly like this. A foundation tier (@iris/core,
@iris/types, @iris/config, @iris/embeddings) owns shared types, errors,
context, configuration, and the canonical embedding client. A conversation
tier owns multi-turn dialogue (@iris/conversation-core),
intent/context/state/style/uncertainty modules, the provider-agnostic
orchestrator (@iris/conversation-orchestration), and concrete provider
adapters for Anthropic, OpenAI, Google, and local Ollama models. An agents
tier (libs/iris/agents/) owns the runtime (@iris/agents-core), archetypes,
multi-agent orchestration, a tool framework, and a full
computer-use/desktop-automation stack (including a real multi-crate Rust native
backend). A knowledge tier (libs/iris/knowledge/) is a production-grade
RAG/GraphRAG/retrieval/grounding stack, and a memory tier
(libs/iris/memory/) implements a four-tier memory hierarchy plus
personalization and privacy sub-trees. Further tiers cover multimodal
(vision, voice, BCI, spatial/XR, IoT), emotional intelligence,
privacy/safety/security, accessibility, platform (gateway, billing,
rate-limiting, SDK codegen, white-label), presence, analytics,
integrations with six sibling Oshun domains, testing, and client
SDKs in five languages.
Honesty note on maturity: the overwhelming majority of these libraries contain
real, domain-specific logic (scoring formulas, retrieval fusion, state machines,
crypto primitives, audio/turn-taking heuristics, statistical tests) and concrete
exported classes/factories — they are not empty scaffolds. Many use injectable
dependency seams and in-memory stores so the algorithms run without external
infrastructure, with real backends (Postgres/Qdrant/Redis, vendor LLM/STT/TTS
APIs) wired behind provider interfaces. A small set of nodes are deliberately
thin V1 product-surface facades — a single index.ts exporting product
metadata, descriptors, and validators (@iris/accessibility, @iris/agents,
@iris/conversation, @iris/multimodal/vision, @iris/multimodal/voice).
Those are called out as such in their entries below rather than overclaimed.
How it fits the wider system#
These libraries are consumed by the Iris product surfaces (web shell,
mobile/desktop companions, the BFF, and the agent loop) and by sibling Oshun
domains through the libs/iris/integrations/* adapters (Hathor, Maya, Nyx,
Psyche, Sophia, Yemaya). The wire contracts for the domain live separately in
@iris/contracts (libs/contracts/iris), which is the bottom-of-graph schema
package the contracts area documents; the libraries here are the
implementation behind those contracts. Provider adapters compose with the
orchestrator; tools and computer-use compose with the agent runtime;
knowledge/RAG and memory compose into the conversation pipeline;
privacy/safety/accessibility wrap every surface. The five SDKs (@iris/sdk and
the Kotlin/Python/Rust/Swift siblings) are the external client view of the same
API. Walk the dependency edges on any node below to see exactly who composes
with it.
Entity catalog (262)#
The 262 tracked Nx projects in iris, each a code-linked entity node — package, type, source path, declared targets, and its internal dependency graph (depends-on / used-by, resolved from the package manifests, §6/§8), read from the project graph. Grouped by architectural layer; walk the dependency links to travel the system. 262 of these carry an authored deep-dive (what / why / how it fits); the rest are generated scaffolds awaiting one.
agent (2)#
Rust native backend (libs/iris/agents/computer-use/native). A multi-crate
workspace (iris-desktop-core traits + per-OS crates for
X11/Wayland/macOS-CGEvent/Windows-SendInput
- an
iris-desktop-napinapi-rs cdylib). X11 has real input/capture and a Task 6.4 native fixture; macOS and Windows have input/capture bodies; Wayland and every native accessibility-tree walker remain incomplete. The README records the per-backend boundary and#[cfg(target_os)]selection.
TypeScript wrapper around the iris/computer-use Rust desktop binding (V1-P2-0093).
TypeScript wrapper (libs/iris/agents/computer-use/native/ts) around the Rust
desktop binding — OshunDesktopController exposes capture, mouse, keyboard,
clipboard, display, and capability methods, while unsupported backend methods
fail closed. DesktopError mirrors the native error categories. Task 6.4 proved
the wrapper plus X11 capture/input path on an isolated GTK/Xvfb target; native
X11 clipboard remains unsupported.
OshunDesktopController14DesktopError14OshunDesktopControllerOptions14ControllerResult14loadNativeBinding21NativeBinding21NativeCapabilities21NativeRegion21NativeCaptureOptions21NativeRawImage21NativeDisplay21NativeClipboardContents21BackendKind32DesktopPoint32 +14 moreagents (1)#
Screenshot understanding and visual UI analysis for AI agents
Screenshot understanding for agents: ScreenAnalyzer, UIElementDetector,
TextExtractor, LayoutAnalyzer, ChangeDetector, wrapped by
ScreenshotVisionAgent.
UIElementId14AnalysisSessionId14RegionId14createUIElementId14createAnalysisSessionId14createRegionId14ScreenshotMetadata14Screenshot14BoundingBox14Point14Color14ElementState14DetectedElement14ElementVisualProperties14 +36 morecontracts (2)#
Unified memory system for Iris AI with four-tier hierarchy (STM, LTM, Episodic, Semantic)
The unified four-tier memory system (STM/LTM/episodic/semantic):
MemoryManager, MemoryTierRouter, MemoryIndex, MemorySerializer, and
MemoryGC.
EpisodeId61ConceptId61IndexId61createMemoryId61createEpisodeId61createConceptId61createIndexId61MEMORY_TIER_ORDER61MEMORY_TIER_NAMES61MemoryImportance61IMPORTANCE_SCORES61getImportanceLevel61STMConfig61DEFAULT_STM_CONFIG61 +88 moreIris AI Assistant shared type definitions
Shared Iris type definitions: conversation/memory/agent/model/user/tool/event
types — a contracts-layer (layer:contracts) package consumed across the area.
MessageId15ThreadId15TurnId15ParticipantRoleSchema15Participant15ParticipantState15ContentTypeSchema15ContentBlockBase15TextContent15TextAnnotation15ImageContent15AudioContent15VideoContent15FileContent15 +307 morecore (1)#
Iris AI Assistant foundation library - configuration, context, errors, logging, and core utilities
Foundation library: shared types, error codes/base, context + correlation/tracer/profiler, a logger, decorators, schemas, and a config loader (~26 modules) — the bottom of the Iris dependency graph.
RequestId14SessionId14ConversationId14MessageId14UserId14AgentId14Failure14Result14AsyncResult14failure14isSuccess14isFailure14SoftDeletable14Versioned14 +237 moredata (1)#
Iris AI memory persistence layer - PostgreSQL, Qdrant, and Redis backends with backup/restore
Durable persistence backends: PostgresStore, QdrantStore (vector),
RedisCache, plus backup/restore/recovery (with an S3 backup client), composed
as a MemoryPersistenceSystem (constructable from env). The real-infrastructure
layer behind the memory tier.
DEFAULT_QDRANT_STORE_CONFIG109DEFAULT_REDIS_CACHE_CONFIG109DEFAULT_BACKUP_CONFIG109DEFAULT_BACKUP_AUTOMATION_CONFIG109DEFAULT_RECOVERY_PROCEDURE_CONFIG109DEFAULT_RESTORE_CONFIG109PostgresMemoryStore124createPostgresMemoryStore124createPostgresMemoryStoreFromEnv124QdrantVectorStore134createQdrantVectorStore134createQdrantVectorStoreFromEnv134createQdrantPayloadFromMemory134RedisCacheStore145 +17 moredomain (67)#
accessibility-* (8)#
Iris accessibility contract for captions, dyslexia-friendly typography, cognitive assistive UI, and screen-reader bridges.
Thin V1 facade. A single index.ts exporting accessibility package
metadata, the V2 companion-bridge descriptor (buildIrisV2AccessibilityBridge),
capability/mode types, and a profile validator — a product-surface catalog, not
the implementing engines (those are the sibling accessibility-* libs).
IRIS_ACCESSIBILITY_PACKAGE_NAME1IRIS_V2_ACCESSIBILITY_BRIDGE_ID2IRIS_V2_PSYCHE_CAPTION_STREAMING_PACKAGE_NAME3IRIS_V2_ACCESSIBILITY_MODULE_PACKAGES5IRIS_V2_ACCESSIBILITY_EVENT_TOPICS12IrisV2AccessibilityClientSurface19IrisV2AccessibilityCapability25IrisV2CognitiveAssistMode32IrisV2ScreenReaderMode34IrisV2AccessibilityProfileInput36IrisV2DyslexiaTypographyTokens48IrisV2CognitiveLoadUiPolicy59IrisV2ScreenReaderBridgePolicy69IrisV2AccessibilityBridge79 +2 moreCognitive accessibility support for Iris - simplified language, step-by-step guidance, and memory aids
Cognitive-accessibility services for users with cognitive disabilities — reading
assistance/pace, simplified language, memory aids, distraction reduction,
step-by-step guidance, text highlighting — with named presets (PRESET_ADHD,
PRESET_READING_SUPPORT, …) and an applyPreset composer. Substantial (~14
modules).
SimplifiedLanguageService63createSimplifiedLanguageService63DEFAULT_SIMPLIFIED_LANGUAGE_CONFIG63COMMON_VOCABULARY63ABBREVIATION_EXPANSIONS63TECHNICAL_TERM_EXPLANATIONS63StepByStepService76createStepByStepService76createGuidanceStep76createGuidanceWorkflow76DEFAULT_STEP_BY_STEP_CONFIG76ConsistentPatternsService88createConsistentPatternsService88createUIPattern88 +42 moreHearing accessibility support for Iris - visual alerts, captioning, and vibration feedback
Hearing-accessibility support for deaf/HoH users: visual alerts, vibration
feedback, real-time captioning, transcript generation, and a sign-language
avatar, composed by createHearingAccessibilityServices.
VisualAlertService163createVisualAlertService163VisualAlertServiceEvents163CaptioningService169createCaptioningService169isSpeechRecognitionAvailable169CaptioningServiceEvents169VibrationFeedbackService176createVibrationFeedbackService176isVibrationSupported176vibrate176VibrationServiceEvents176TranscriptGenerationService184createTranscriptGenerationService184 +9 moreInternationalization support for Iris - multi-language, RTL layouts, cultural adaptation, and localized formatting
Internationalization layer (~16 modules) — language support, RTL layout,
cultural adaptation, localized date/number formats, translation memory,
real-time/UI/content translation — with ~11 locale presets (I18N_PRESET_AR_SA,
_JA, _ZH_CN, …).
LanguageSupportService69createLanguageSupportService69DEFAULT_LANGUAGE_SUPPORT_CONFIG69LANGUAGE_DATABASE69SCRIPT_FONT_STACKS69RTLLayoutService77createRTLLayoutService77DEFAULT_RTL_LAYOUT_CONFIG77LOGICAL_PROPERTY_MAP77RTL_TRANSFORM_RULES77BIDI_CLASSES77CulturalAdaptationService86createCulturalAdaptationService86DEFAULT_CULTURAL_ADAPTATION_CONFIG86 +49 moreMotor accessibility and voice-only operation support for Iris
Motor-accessibility / voice-only operation: voice recognition, voice
commands/navigation, dictation, switch access, eye tracking, predictive and
custom input, via createMotorAccessibilityServices.
VoiceRecognitionService172createVoiceRecognitionService172VoiceRecognitionServiceEvents172VoiceCommandsService178createVoiceCommandsService178VoiceCommandsServiceConfig178VoiceCommandsServiceEvents178VoiceNavigationService185createVoiceNavigationService185VoiceNavigationServiceEvents185DictationService191createDictationService191DictationServiceEvents191VoiceOnlyModeService197 +50 moreVisual accessibility and screen reader support for Iris
Visual accessibility / screen-reader support: ScreenReaderOptimization,
ARIALabels, FocusManagement, KeyboardNavigation, AnnouncementSystem, via
createVisualAccessibility.
ScreenReaderOptimization40ARIALabels41FocusManagement42KeyboardNavigation43AnnouncementSystem44VisualAccessibilityConfig57VisualAccessibility83createVisualAccessibility319Visual alternatives including high contrast, audio descriptions, and spatial audio for Iris
Visual alternatives — HighContrastModes, AudioDescriptions,
TextAlternatives, SpatialAudioNavigation — composed by the
VisualAlternatives class.
HighContrastModes35AudioDescriptions36TextAlternatives37SpatialAudioNavigation38VisualAlternativesConfig58VisualAlternatives73createVisualAlternatives262Adjustable display settings including text sizing, color contrast, font choices, and reduced motion for Iris
Adjustable-display controls: TextSizing, ColorContrast, FontChoices,
ReducedMotion, composed by createAdjustableDisplay.
TextSizing36ColorContrast37FontChoices38ReducedMotion39AdjustableDisplayConfig62AdjustableDisplay193createAdjustableDisplay456code-* (6)#
Agentic coding capabilities with multi-file operations, refactoring, bug fixing, and feature implementation
Agentic coding: AgenticCoder, MultiFileChanger, RefactoringEngine,
BugFixer, FeatureImplementer for multi-file code operations.
DEFAULT_AGENTIC_CONFIG67CodeLocationSchema70FileChangeSchema70BugReportSchema70FeatureSpecSchema70RefactoringRequestSchema70AgenticCoder79createBugReportFromError79createFeatureSpecFromStory79createFeatureSpecFromRequirements79MultiFileChanger87createFile87modifyFile87deleteFile87 +22 moreComprehensive code generation library with builders, generators, test generation, documentation generation, and contextual autocomplete
Code generation: a TypeScript AST generator with fluent builders
(expression/statement/ function/class), test-generator, doc-generator, and
contextual autocomplete.
DEFAULT_CODE_GENERATION_CONFIG206CodeGenerationError206FormattingConfigSchema206ImportConfigSchema206CommentConfigSchema206NamingConfigSchema206CodeGenerationConfigSchema206literal220string220number220boolean220nullLiteral220undefinedLiteral220regex220 +111 moreCode reasoning and analysis library for Iris conversation engine
Code reasoning (libs/iris/conversation/reasoning/code): AST/static analysis, a
RuntimeBehaviorPredictor, and a BugHypothesisGenerator, composed as
CodeReasoner.
ParseErrorCode107createAnalysisId110createAstNodeId110createBugHypothesisId110DEFAULT_CODE_REASONER_CONFIG113DEFAULT_STATIC_ANALYSIS_CONFIG113DEFAULT_RUNTIME_PREDICTOR_CONFIG113DEFAULT_BUG_HYPOTHESIS_CONFIG113CodeReasoner121StaticAnalysisIntegration122RuntimeBehaviorPredictor123BugHypothesisGenerator124Semantic code analysis library providing control flow graphs, data flow analysis, function purpose inference, and variable tracking
Semantic code analysis: ControlFlowAnalyzer, DataFlowAnalyzer,
FunctionPurposeInference, VariableUsageTracker, composed as
SemanticAnalyzer.
SemanticAnalyzer11createSemanticAnalyzer11analyzeSemantics11ControlFlowAnalyzer14DataFlowAnalyzer17FunctionPurposeInference20VariableUsageTracker23DEFAULT_SEMANTIC_ANALYZER_CONFIG84SemanticAnalyzerConfigSchema84SemanticAnalysisError84Sandboxed code execution for agents: PythonRunner, TypeScriptRunner,
ShellRunner over a code-executor/sandbox with output capture, composed as
CodeTools.
SandboxId14LanguageVersion14ExecutionOptions14ExecutionRequest14ExecutionFile14ExecutionResult14ExecutionOutputFile14ResourceUsage14SandboxType14SandboxMount14SandboxStatus14IPythonRunner14ITypeScriptRunner14IShellRunner14 +78 moreCode intelligence system for deep multi-language code understanding with AST parsing, type inference, call graph analysis, and data flow tracking
Multi-language code intelligence: AstParser, SymbolExtractor,
TypeInference, CallGraph, DataFlow, composed as CodeAnalyzer (the base
the language analyzers extend).
DEFAULT_PARSER_CONFIG73DEFAULT_ANALYSIS_CONFIG73getLanguageFamily73isStaticallyTyped73createTypeInfo73ASTParser93createASTParser93arseSource93arseNormalizedSource93raverseAST93findNodes93findNode93findNodesByType93findNodesBySemanticType93 +49 moreconversation-* (7)#
Production assistant conversation facade for Iris
Thin V1 facade. Single index.ts for a production-assistant transcript
surface — metadata, IrisProductionAssistant* types, and
create*/validate*/serialize* transcript functions — not the conversation
engine (that is @iris/conversation-core).
IRIS_CONVERSATION_METADATA1getIrisConversationMetadata16IrisProductionAssistantTopic20IrisProductionAssistantUrgency21IrisProductionAssistantSource23IrisProductionAssistantQuestion32IrisProductionAssistantAnswer40IrisProductionAssistantTranscript52IrisProductionAssistantTranscriptInput63IrisConversationValidationIssue73IrisConversationValidationResult85createIrisProductionAssistantTranscript222validateIrisProductionAssistantTranscript265serializeIrisProductionAssistantTranscript336Conversation branching system for exploring alternate dialogue paths
Conversation branching: BranchManager, BranchMerger, BranchSummarizer,
BranchHistory for alternate dialogue paths.
BranchPointId14ConversationId14MessageId14MergeId14SnapshotId14createBranchPointId14createConversationId14createMessageId14createMergeId14createSnapshotId14ConversationMessage14BranchType14BranchReason14BranchPoint14 +73 moreSemantic context tracking for conversations including topics, entities, and context compression
Semantic context tracking: TopicDetector, EntityTracker,
ContextCompressor, ContextSummarizer, composed as ContextTracker.
createTopicId85createEntityId85DEFAULT_TOPIC_DETECTOR_CONFIG91DEFAULT_ENTITY_TRACKER_CONFIG91DEFAULT_CONTEXT_TRACKER_CONFIG91DEFAULT_COMPRESSION_CONFIG91DEFAULT_SUMMARY_CONFIG91TopicDetector103createTopicDetector103EntityTracker109createEntityTracker109ContextCompressor115createContextCompressor115ContextSummarizer121 +4 moreCore dialogue engine for managing multi-turn conversations
The core dialogue engine (~28 modules): ConversationManager (session
lifecycle), TurnManager, ConversationHistory, context-window management,
dialogue state, streaming response generator, plus
search-index/bookmarks/highlights/tags/sharing and an in-memory storage backend.
ContextWindow107createContextWindow107stimateMessageTokens107DEFAULT_CONTEXT_WINDOW_CONFIG107DialogueStateMachine118createDialogueStateMachine118isDialogueState118TurnManager128createTurnManager128DEFAULT_TURN_MANAGER_CONFIG128ConversationHistory134createConversationHistory134ConversationManager140createConversationManager140 +81 moreIntent recognition and classification system for conversations
Intent recognition (~36 modules): IntentClassifier, QuestionDetector,
UrgencyDetector, SlotFiller, plus an extensive Direct-Command-Control
(dcc-*) voice-session suite (intent decomposition, agent-delegation routing,
voice confirmation/handoff, multi-user isolation).
createIntentId219DEFAULT_INTENT_CLASSIFIER_CONFIG225DEFAULT_QUESTION_DETECTOR_CONFIG225DEFAULT_URGENCY_DETECTOR_CONFIG225DEFAULT_SLOT_FILLER_CONFIG225IntentClassifier236createIntentClassifier236DCCIntentClassifier242createDCCIntentClassifier242DCCConversationContextMemory248createDCCConversationContextMemory248DCCIntentDecomposer257createDCCIntentDecomposer257DCCStatusSpeechRenderer263 +74 moreConversation summarization with incremental summaries, key points, and action items
Long-thread summarization: ConversationSummarizer, KeyPointExtractor,
ActionItemExtractor (incremental summaries).
KeyPointId14ActionItemId14MessageId14ConversationId14createKeyPointId14createActionItemId14createMessageId14createConversationId14ConversationMessage14SummaryFormat14SummaryStatus14ConversationSummary14IncrementalSummaryState14PriorityLevel14 +19 moreReusable conversation templates with variables, conditions, and branching
Reusable conversation templates: registry, variable substitution, conditional
branching, a fluent builder, and TemplateExecutor.
StepId15VariableId15ConditionId15InstanceId15createStepId15createVariableId15createConditionId15createInstanceId15VariableSource15TemplateVariable15VariableValues15VariableValidationResult15LogicalOperator15ConditionExpression15 +59 morepersonalization-* (5)#
Comprehensive user modeling and personalization system for Iris AI
User-modeling and personalization (libs/iris/memory/personalization, ~30
modules): preference/interest/goal trackers, ExpertiseEstimator,
BehaviorAnalyzer, Big-Five detection, context-fusion/prediction,
location/device context, and a UserModelStore, composed as
PersonalizationSystem.
createPreferenceId108createInterestId108createGoalId108createBehaviorId108createExpertiseId108DEFAULT_INTEREST_TRACKER_CONFIG108DEFAULT_GOAL_TRACKER_CONFIG108DEFAULT_EXPERTISE_ESTIMATOR_CONFIG108DEFAULT_BEHAVIOR_ANALYZER_CONFIG108DEFAULT_DEVICE_PREFERENCES108DEFAULT_COMMUNICATION_STYLE108DEFAULT_ADAPTATION_STATE108PreferenceTracker135createPreferenceTracker135 +177 moreFeedback learning system for personalization - collection, detection, processing, and adaptation
Feedback-learning for personalization
(libs/iris/memory/personalization/feedback): FeedbackCollector,
ImplicitFeedbackDetector, FeedbackProcessor, AdaptationEngine.
createFeedbackId102createSignalId102createAdaptationRuleId102createLearningSessionId102createAggregationId102DEFAULT_IMPLICIT_DETECTOR_CONFIG111DEFAULT_FEEDBACK_COLLECTOR_CONFIG111DEFAULT_ADAPTATION_ENGINE_CONFIG111FeedbackCollector121InMemoryFeedbackStore121FeedbackCollectorEvents121IFeedbackStore121FeedbackStatistics121ImplicitFeedbackDetector133 +16 morePreference inference system for learning user preferences from behavioral signals
Preference inference: PreferenceInferrer, StyleAnalyzer, InterestDetector,
ConfidenceTracker, composed as an InferenceSystem.
createInferenceId100createInferenceSignalId100createTopicId100createStyleProfileId100createConfidenceRecordId100DEFAULT_PREFERENCE_INFERRER_CONFIG112DEFAULT_STYLE_ANALYZER_CONFIG112DEFAULT_INTEREST_DETECTOR_CONFIG112DEFAULT_CONFIDENCE_TRACKER_CONFIG112PreferenceInferrer123createPreferenceInferrer123InMemoryInferenceStore123InMemorySignalStore123StyleAnalyzer134 +12 moreUser segmentation system for personalization clustering, defaults, and transition tracking
User segmentation: profile clustering/ranking, segment assignment with smoothing, segment-default behavior packs, and transition/stability metrics.
createSegmentProfileId44createSegmentAssignmentId44createSegmentTransitionId44DEFAULT_SEGMENTATOR_CONFIG44InMemorySegmentProfileStore51SegmentProfilesService51createSyntheticVector51createSegmentProfilesService51InMemorySegmentDefaultsStore58SegmentDefaultsService58createSegmentDefaultsService58InMemorySegmentTransitionStore64SegmentTransitionTracker64createSegmentTransitionTracker64 +3 moreA/B testing framework for personalization strategies
Personalization A/B testing: experiment lifecycle, VariantAssignmentService,
outcome measurement, and statistical experiment analysis.
createPersonalizationExperimentId37createPersonalizationVariantId37createVariantAssignmentId37createOutcomeMeasurementId37DEFAULT_PERSONALIZATION_TESTING_CONFIG37VariantAssignmentService45createVariantAssignmentService45OutcomeMeasurementService47createOutcomeMeasurementService47ExperimentAnalysisService52createExperimentAnalysisService52InMemoryExperimentStore57InMemoryAssignmentStore57InMemoryOutcomeStore57 +2 moreprivacy-* (5)#
Memory privacy and user control system for Iris AI
Memory privacy/user-control (libs/iris/memory/privacy, ~30 modules): memory
viewer/editor/ deleter/exporter/importer, opt-out, consent manager, retention
policy, PII redactor, differential privacy (noise injector, privacy budget), E2E
encryption, key management, and a local store. (Note: distinct from the
privacy/* tier libraries.)
ExportId15ImportId15MemoryViewFilter15MemoryViewSort15MemoryViewPagination15MemoryViewOptions15MemoryViewEntry15MemoryViewResult15MemoryViewStats15MemoryEditableFields15MemoryEditOptions15MemoryEditResult15MemoryBatchEdit15MemoryBatchEditResult15 +211 moreComprehensive access control, permissions, OAuth/OIDC integration, and audit logging for privacy-preserving AI systems
Access control (~9 modules): permissions/conditions engine, API-key management, OAuth2 + OIDC services, audit logging, and a rate limiter — the access-control layer for privacy-preserving systems.
CLASSIFICATION_LEVELS84PrincipalTypeSchema87ResourceTypeSchema87DataClassificationSchema87PermissionEffectSchema87ConditionOperatorSchema87OAuth2GrantTypeSchema87AuditEventCategorySchema87AuditEventSeveritySchema87CreateApiKeyRequestSchema87AuthorizationRequestSchema87TokenRequestSchema87AuditQueryFiltersSchema87AuditQueryOptionsSchema87 +21 moreBehavioral safety and abuse prevention for AI systems
Behavioral safety/abuse prevention: action confirmation, sandboxed execution,
rate limiting, and anomaly detection, composed as BehavioralSafety.
ActionConfirmation14createActionConfirmation14DEFAULT_HIGH_STAKES_ACTIONS14ActionConfirmationConfig14SandboxedExecution21createSandboxedExecution21DEFAULT_RESOURCE_LIMITS21DEFAULT_CAPABILITIES21DEFAULT_BLOCKED_PATHS21DEFAULT_BLOCKED_HOSTS21DEFAULT_SECURITY_POLICIES21SANDBOX_PRESETS21SandboxedExecutionConfig21RateLimiter33 +11 moreOutput validation for AI safety including PII detection, bias detection, and factuality checking
Output validation: PIIDetector, BiasDetector, FactualityChecker, composed
as an OutputValidationSystem.
OutputValidator31createOutputValidator31DEFAULT_VALIDATION_RULES31DEFAULT_OUTPUT_VALIDATOR_CONFIG31PIIDetector38createPIIDetector38DEFAULT_PII_PATTERNS38DEFAULT_PII_DETECTOR_CONFIG38BiasDetector45createBiasDetector45DEFAULT_BIAS_INDICATORS45DEFAULT_BIAS_DETECTOR_CONFIG45FactualityChecker52createFactualityChecker52 +6 moreComprehensive secret management, credential handling, and leak detection for Iris
Secret management: SecretStore, CredentialManager, rotation, and a leak
scanner.
SecretStatusSchema65SecretClassificationSchema65RotationStrategySchema65CredentialTypeSchema65SensitiveDataTypeSchema65ScanSeveritySchema65SecretAccessTypeSchema65CreateSecretRequestSchema65UpdateSecretRequestSchema65ScanContentRequestSchema65InMemorySecretStorage87createSecretStoreWithStorage87InMemoryCredentialStorage103createCredentialManagerWithStorage103 +9 moretool-* (5)#
Secure tool authentication: ToolCredentialManager, OAuthToolAuth,
APIKeyToolAuth, CredentialRefresh.
DEFAULT_TOOL_CREDENTIAL_MANAGER_CONFIG22DEFAULT_CREDENTIAL_REFRESH_CONFIG22ToolCredentialManager27createToolCredentialManager27OAuthToolAuth29createOAuthToolAuth29APIKeyToolAuth31createAPIKeyToolAuth31CredentialRefresh33createCredentialRefresh33Tool-workflow composition: ToolComposer, ToolPipeline, parallel executor,
and conditional branching for complex tool graphs.
DEFAULT_PARALLEL_EXECUTOR_CONFIG28ToolComposer30createToolComposer30ParallelToolExecutor32createParallelToolExecutor32StepExecutor32ConditionalToolBranching38createConditionalToolBranching38ToolPipeline43createToolPipeline43Tool marketplace: discovery, installation, rating, and ToolCertification
(trust) services.
ToolMarketplace19createToolMarketplace19ToolInstaller21createToolInstaller21ToolRatingSystem23createToolRatingSystem23ToolCertification25createToolCertification25ToolMarketplaceService27createToolMarketplaceService27Tool-execution observability: ToolExecutionMonitor, ToolErrorTracking,
ToolUsageAnalytics, performance metrics, composed as ToolMonitoringSuite.
DEFAULT_TOOL_MONITORING_CONFIG37DEFAULT_REGRESSION_THRESHOLDS37DEFAULT_ERROR_TRACKING_CONFIG37classifyToolErrorCategory37defaultSeverityForCategory37normalizeErrorSignature37createEmptyDistribution37createRunId37ToolExecutionMonitor48createToolExecutionMonitor48ToolPerformanceMetrics50createToolPerformanceMetrics50ToolErrorTracking55createToolErrorTracking55 +4 moreTool version/migration management with a real semver implementation
(parseSemver, compareSemver, satisfiesConstraint), ToolMigrationUtils,
deprecation handling, and a compatibility checker.
DEFAULT_TOOL_VERSION_MANAGER_CONFIG20arseSemver24compareSemver24incrementVersion24satisfiesConstraint24VersionCompatibilityChecker26createVersionCompatibilityChecker26ToolMigrationUtils31createToolMigrationUtils31DeprecationHandling33createDeprecationHandling33ToolVersionManager35createToolVersionManager35vision-* (5)#
Production footage analysis facade for Iris multimodal vision tools
Thin V1 facade. Single index.ts for a production-footage analysis surface
— metadata, IrisVision* types, default required-domains/quality-profile, and
create*/validate*/ serialize* packet functions — not the vision engines
(those are the vision-* libs).
IRIS_MULTIMODAL_VISION_METADATA1getIrisMultimodalVisionMetadata14IrisVisionAnalysisDomain18IrisVisionIssueSeverity22IrisVisionFrameObservation24IrisVisionContinuityExpectation41IrisVisionQualityProfile49IrisVisionProductionFootagePacketInput62IrisVisionContinuityMatch75IrisVisionTakeAnalysis84IrisVisionProductionFootagePacket99IrisVisionValidationIssue116IrisVisionValidationResult130DEFAULT_IRIS_VISION_REQUIRED_DOMAINS135 +4 moreDocument parsing and analysis for the Iris AI domain
Document parsing: PDF/form/receipt/table extraction and layout analysis via a
DocumentParser, with a large helper surface (currency formatting, bounding-box
math, reading-order sorting, tableToCSV).
DEFAULT_PDF_PARSING_CONFIG96DEFAULT_FORM_EXTRACTION_CONFIG96DEFAULT_RECEIPT_PARSING_CONFIG96DEFAULT_TABLE_EXTRACTION_CONFIG96DEFAULT_LAYOUT_ANALYSIS_CONFIG96createPageId108createElementId108createTableId108createFormFieldId108createReceiptId108FormExtractor108ReceiptParser108TableExtractor108LayoutAnalyzer108 +35 moreImage generation and editing module for Iris multimodal AI
Image generation/editing: a generation-impl with image creation, edit
operations, diagram generation, and screenshot annotation, plus
color/aspect-ratio/file-size helpers and model/ format constant tables.
DEFAULT_IMAGE_GENERATION_CONFIG81DEFAULT_IMAGE_EDITING_CONFIG81DEFAULT_DIAGRAM_CREATION_CONFIG81DEFAULT_DIAGRAM_THEME81DEFAULT_SCREENSHOT_ANNOTATION_CONFIG81DEFAULT_ANNOTATION_STYLE81createImageId94createDiagramId94createAnnotationId94createEditOperationId94ImageEditor94DiagramCreator94ScreenshotAnnotator94createImageEditor94 +33 moreComprehensive image understanding including object detection, scene description, OCR, and chart interpretation
Image understanding: object detection, scene description, OCR (50+ languages),
and chart interpretation via an ImageAnalyzer, with IoU/bounding-box math and
OCR-language tables.
DEFAULT_OBJECT_DETECTION_CONFIG97DEFAULT_SCENE_DESCRIPTION_CONFIG97DEFAULT_OCR_CONFIG97DEFAULT_CHART_INTERPRETATION_CONFIG97DEFAULT_IMAGE_ANALYSIS_CONFIG97createDetectionId109createSceneDescriptionId109createOCRResultId109createChartAnalysisId109ObjectDetector109SceneDescriptor109TextExtractor109ChartInterpreter109createObjectDetector109 +38 moreVideo understanding module for Iris multimodal AI
Video understanding: a VideoAnalyzer for analysis, action recognition,
temporal reasoning, summarization, and key-frame extraction, with
timestamp/frame-rate/bitrate helpers and codec/resolution tables.
DEFAULT_VIDEO_ANALYSIS_CONFIG93DEFAULT_ACTION_RECOGNITION_CONFIG93DEFAULT_TEMPORAL_REASONING_CONFIG93DEFAULT_SUMMARIZATION_CONFIG93DEFAULT_KEYFRAME_EXTRACTION_CONFIG93createFrameId105createSegmentId105createActionId105createTrackId105createSceneId105ActionRecognizer105TemporalReasoner105VideoSummarizer105KeyFrameExtractor105 +41 moreeverything else (26)#
Custom agent builder framework for Iris AI Assistant
Custom-agent builder framework (libs/iris/platform/customization/agents, ~21
modules): AgentBuilder, ToolBuilder, PersonaBuilder, a TemplateRegistry
with built-in templates, plus template marketplace/installer/publisher/rating
and a creation wizard.
AgentBuilder61createAgentBuilder61ToolBuilder64createToolBuilder64createTool64createWebSearchTool64createCodeExecutionTool64createFileReadTool64createApiCallTool64createDatabaseQueryTool64ToolRegistry64createToolRegistry64getGlobalToolRegistry64resetGlobalToolRegistry64 +52 moreMobile-safe Iris agent umbrella catalog for built-in assistant agents and launch readiness.
Thin V1 facade. Single index.ts exposing the built-in-agent catalog
(listIrisBuiltInAgents, getIrisBuiltInAgent), capability/intent types,
selectIrisAgentForIntent, and a launch-readiness resolver — a product-surface
descriptor layer over the real agents-* runtime libs.
IRIS_AGENTS_PACKAGE_NAME1IRIS_BUILT_IN_AGENT_IDS3IrisBuiltInAgentId15IrisAgentSurface17IrisAgentCapability19IrisAgentToolCategory34IrisAgentIntent44IrisBuiltInAgentDescriptor54IrisAgentFilter67IrisAgentSelectionInput73IrisAgentsLaunchReadinessInput79IrisAgentsLaunchReadiness84listIrisBuiltInAgents224getIrisBuiltInAgent242 +2 moreCore agent framework for Iris AI - runtime, lifecycle, context, communication, and permissions
The agent runtime framework (~36 modules):
context/lifecycle/communication/permission managers, AgentRuntime,
AgentSystem, a tool-registry, provider adapters, a cognition gateway,
budget, reward/recommendation models, execution replay/learning, and an
oshun-ai-bridge. The substantive heart of the agents tier.
TaskId14SessionId14MessageId14TaskState14AgentPriority14AgentInfo14AgentError14AgentTask14Task14TaskResult14ContextValue14ContextScope14ContextConfig14MessageType14 +132 moreAnalytics system for the Iris AI Assistant framework with privacy-compliant collection, metrics aggregation, and retention policies
Privacy-compliant analytics engine (~14 modules): analytics-engine,
event-tracker, metrics-aggregator, retention/usage/quality, plus
launch-monitoring, incident-response, and a runbook-executor.
AnalyticsSessionId14MetricId14AnalyticsUserId14createAnalyticsSessionId14createMetricId14createAnalyticsUserId14EventSeverity14AnalyticsEvent14EventMetadata14AnalyticsEventInput14EventCategorySchema14EventSeveritySchema14AggregationMethod14TimeWindow14 +191 moreAPI-integration tools for agents: APIClient, RateLimiter, OAuthHandler
(with OAuthProviders), ResponseParser, composed as APITools.
EndpointId14OAuthToken14APIKey14HTTPHeaders14QueryParams14ContentType14RequestBody14HTTPRequestOptions14HTTPResponse14AuthConfig14OAuth1Config14OAuth2Config14OAuth2GrantType14OAuth2TokenResponse14 +37 moreIris intake agent for Concordia — trauma-aware, multilingual, authority-aware private intake (Phase 179.3.1).
Iris intake state machine for the Concordia mediation domain (§179.3.1, Phase
179, ~21 source modules): trauma-/coercion-aware safety-signal detection and a
runSafetyPipeline routing to Kuanyin restorative circles, hard-boundary gates,
multi-device/party-isolated intake, language detection/drift, and human-reviewer
queues.
detectStatementConsistency12ConsistencyReport12DetectStatementConsistencyInput12InconsistencyFinding12InconsistencyKind12InconsistencySeverity12PartyTimelineClaim12PartyTimelineEntry12TimelineStage12deriveReviewFlags25xtractCommitments25roposeClauses25urnConversationIntoAgreement25ConversationCommitment25 +231 moreSelf-consistency checking with contradiction detection, belief tracking, and repair
Self-consistency checking: ContradictionDetector, BeliefTracker,
ConsistencyRepair, composed as ConsistencyChecker/ConsistencySystem with
quick-check helpers.
createStatementId92createContradictionId92createRepairId92createConsistencySessionId92createJustificationId92DEFAULT_CONTRADICTION_DETECTOR_CONFIG92DEFAULT_BELIEF_TRACKER_CONFIG92DEFAULT_CONSISTENCY_REPAIR_CONFIG92ConsistencyChecker115createConsistencyChecker115ContradictionDetector118createContradictionDetector118BeliefTracker120createBeliefTracker120 +7 moreThe canonical embedding client for Oshun: a three-tier facade (tier1 OpenAI
text-embedding-3-large, tier2 Voyage voyage-3-large, tier3 local BGE-M3)
with cache/ disk-cache, metrics, migration, evaluation, an in-process embedder,
and a multilingual benchmark. Decision-doc-grounded
(docs/releases/p2/embeddings-provider-decision.md).
IrisEmbeddingClientImpl10createIrisEmbeddingClient10cosineSimilarity10IrisEmbeddingClient10IrisEmbeddingClientConfig10createInProcEmbeddingClient18InProcEmbeddingClientOptions18EmbeddingTierSchema23TIER_DEFAULTS23EmbeddingRequestSchema23BatchEmbeddingRequestSchema23EmbeddingTenantIdSchema23EmbeddingTier23TierDefault23 +42 moreFile system tools for Iris AI agents - read, write, search, watch
File-system tools: PermissionChecker,
FileReadTool/FileWriteTool/FileSearchTool, DirectoryTool,
FileWatchTool, composed as FileSystemTools.
WatchId14createFilePath14createWatchId14PermissionScope14PermissionCheckResult14PermissionConfig14DEFAULT_PERMISSION_CONFIG14FileStats14FileReadResult14FileWriteResult14SafetyConfig14SafetyCheckResult14DEFAULT_SAFETY_CONFIG14FileSearchOptions14 +35 moreFunction-calling framework: ParameterParser, ResultHandler, ErrorHandler,
TimeoutManager, FunctionCaller, composed as FunctionCallingSystem.
ExecutionId29createExecutionId29ErrorSeverity29ErrorCategory29ParameterIssue29ParameterParseResult29ParameterParserConfig29ParameterSchema29ParameterType29ParameterConstraints29CallMetadata29ExecutionOptions29ResourceLimits29FunctionCallError29 +32 moreIoT integration module for smart home and sensor integration
IoT/smart-home integration: device control across HomeKit/Google-Home/Alexa/SmartThings, room/scene management, automation rules, and sensor data, with extensive platform/device/ sensor constant tables and unit-conversion helpers.
DEFAULT_SMART_HOME_CONFIG96DEFAULT_SENSOR_INTEGRATION_CONFIG96createHubId102createRoomId102createSceneId102createAutomationId102createSensorId102createEventId102SensorDataIntegration102createSensorDataIntegration102SMART_HOME_PLATFORMS143DEVICE_CATEGORIES161DEVICE_CAPABILITIES189ROOM_TYPES216 +16 moreProduction-grade RAG (Retrieval Augmented Generation) pipeline for Iris
Production-grade RAG pipeline: query processing (expansion/decomposition/HyDE),
hybrid retrieval with an in-memory BM25 index + RRF fusion, cross-encoder
reranking, response generation, caching, and evaluation, composed as
DefaultRAGPipeline.
createDocumentId84createChunkId84createQueryId84createRetrievalSessionId84createCitationId84DEFAULT_RAG_CONFIG84DocumentMetadataSchema94DocumentSchema94ChunkMetadataSchema94ChunkSchema94ChunkSemanticTypeSchema94QueryTypeSchema94QueryComplexitySchema94RAGQuerySchema94 +37 moreKnowledge type handling for factual, procedural, conceptual, and experiential knowledge
Knowledge type system: factual/procedural/conceptual/etc. types, a
knowledge-factory, confidence scoring, retrieval strategies, and Zod type
schemas.
createFactualKnowledgeId96createProceduralKnowledgeId96createConceptualKnowledgeId96createExperientialKnowledgeId96createGenericKnowledgeId96createSourceId96createUserId96createAgentId96createPreferenceId96isFactualKnowledge109isProceduralKnowledge109isConceptualKnowledge109isExperientialKnowledge109DEFAULT_CONFIDENCE_SCORE117 +69 moreMathematical reasoning with symbolic computation, equation solving, unit conversion, and statistical analysis
Mathematical reasoning: expression parse/eval, symbolic computation,
EquationSolver, UnitConverter (dimensional analysis), StatisticalReasoner,
composed as MathReasoner.
ParseErrorCode91ComputationErrorCode91UnitErrorCode91createExpressionId94createSolutionId94createComputationId94DEFAULT_MATH_REASONING_CONFIG97DEFAULT_EQUATION_SOLVER_CONFIG97DEFAULT_STATISTICAL_CONFIG97DEFAULT_UNIT_CONVERTER_CONFIG97MathReasoner105EquationSolver106UnitConverter107formatDimension107 +2 moreSemantic memory system for knowledge graphs, concepts, and reasoning
Semantic memory: knowledge graphs, ConceptUnderstanding,
RelationshipTracker, DomainExpertiseModel, UserKnowledgeGraph,
SemanticInference, composed as SemanticMemory.
createEntityId84generateEntityId84createDomainId84generateDomainId84createInferenceId84generateInferenceId84DEFAULT_RELATIONSHIP_TRACKER_CONFIG94DEFAULT_DOMAIN_EXPERTISE_CONFIG94DEFAULT_USER_KNOWLEDGE_GRAPH_CONFIG94DEFAULT_CONCEPT_UNDERSTANDING_CONFIG94DEFAULT_SEMANTIC_INFERENCE_CONFIG94RelationshipTracker103createRelationshipTracker103findCommonEntities104 +27 moreMetacognitive monitoring with confidence calibration, knowledge gap detection, and learning opportunity identification
Metacognitive monitoring: ConfidenceCalibration, KnowledgeGapDetector,
LearningOpportunityIdentifier, composed as MetacognitiveMonitor.
createAssessmentId85createPredictionId85createGapId85createOpportunityId85createMetacognitiveSessionId85DEFAULT_CALIBRATION_CONFIG94DEFAULT_METACOGNITIVE_CONFIG94DEFAULT_GAP_DETECTOR_CONFIG94DEFAULT_LEARNING_OPPORTUNITY_CONFIG94DEFAULT_QUALITY_WEIGHTS94MetacognitiveErrorCode103MetacognitiveError103ConfidenceCalibration106createConfidenceCalibration106 +6 moreProduction voice command facade for Iris multimodal voice tools
Thin V1 facade. Single index.ts for a production voice-command surface —
metadata, IrisVoiceProduction* types, default command definitions routing to
drone-fleet/switcher/ recorder, and packet create*/validate*/serialize*
functions — not the voice engines.
IRIS_MULTIMODAL_VOICE_METADATA1getIrisMultimodalVoiceMetadata15IrisVoiceProductionCommandCategory19IrisVoiceProductionCommandRisk20IrisVoiceProductionRoute21IrisVoiceProductionUtterance23IrisVoiceProductionCommandDefinition33IrisVoiceProductionCommand43IrisVoiceProductionCommandPacket59IrisVoiceProductionCommandPacketInput74IrisVoiceValidationIssue85IrisVoiceValidationResult99DEFAULT_IRIS_VOICE_PRODUCTION_COMMANDS104createIrisVoiceProductionCommandPacket226 +2 moreEnterprise SLA management for Iris platform
Enterprise SLA management: an sla-manager for contract tracking, breach
detection, incident management, and compliance reporting (barrel re-exports
sla-manager/types).
Cross-service integration with Oshun ecosystem for Iris presence
Cross-service presence integration: per-domain integrations
(Maya/Yemaya/Hathor/Nyx + a generic Oshun one) composed as
UnifiedOshunIntegration.
IntegrationActions23OshunServiceIntegration26MayaIntegration29YemayaIntegration30HathorIntegration31NyxIntegration32UnifiedOshunIntegration44createOshunIntegration113Cross-device synchronization for seamless Iris presence experience
Cross-device presence sync: ConversationContinuityManager,
TaskHandoffManager, NotificationUnificationManager, PreferenceSyncManager,
StateSyncManager, composed as PresenceSyncManager.
DEFAULT_SYNC_CONFIG28ConversationContinuityManager31TaskHandoffManager34TaskContinuityHelper34NotificationUnificationManager37PreferenceSyncManager40PreferenceValidators40StateSyncManager43PresenceSyncManager59createPresenceSyncManager330Scientific reasoning library for research-grade analysis, hypothesis generation, citation validation, and experiment design
Scientific reasoning: ScientificReasoner, CitationValidator,
HypothesisGenerator, ExperimentDesigner, and retraction services.
ScientificErrorCode103DEFAULT_SCIENTIFIC_REASONER_CONFIG106DEFAULT_CITATION_VALIDATOR_CONFIG106DEFAULT_HYPOTHESIS_GENERATOR_CONFIG106DEFAULT_EXPERIMENT_DESIGNER_CONFIG106createHypothesisId106createCitationId106createExperimentId106createEvidenceId106createResearchSessionId106createVariableId106createConfidenceScore106createPValue106createEffectSize106 +30 moreAR/XR spatial computing (Vision Pro/Quest/Android XR/HoloLens): XR session
management, spatial anchors, eye/gaze + hand-tracking, plane detection, and a
real 3D-math toolkit (createPose, rayPlaneIntersection,
raySphereIntersection, bounding-box ops).
DEFAULT_XR_SESSION_CONFIG153DEFAULT_GAZE_INTERACTION_CONFIG153DEFAULT_GESTURE_RECOGNITION_CONFIG153DEFAULT_ENVIRONMENT_UNDERSTANDING_CONFIG153DEFAULT_SPATIAL_UI_STYLE153createAnchorId165createEntityId165createGestureId165createPlaneId165createMeshId165vec3Add165vec3Subtract165vec3Scale165vec3Magnitude165 +45 moreFormal structured reasoning with logic validation, premise tracking, and inference
Formal structured reasoning: PremiseTracker, LogicValidator,
ConclusionDeriver, ReasoningExplainer, composed as StructuredReasoner.
ConclusionId44ArgumentId44InferenceId44ReasoningSessionId44ProofId44createConclusionId44createArgumentId44createInferenceId44createReasoningSessionId44createProofId44PremiseSource44PremiseStatus44Premise44LogicalVariable44 +44 moreTool registry system for agent tool management
Tool registry: schema management, ToolValidation, ToolDiscovery, and
versioning, composed as ToolRegistrySystem.
ToolVersion14SchemaId14createToolVersion14createSchemaId14ToolCategory14ToolCapability14JsonSchemaFormat14JsonSchema14ToolReturn14ToolError14ToolSchema14ToolLimits14ToolSecurityRequirements14ToolDefinition14 +33 moreVoice provider abstraction, voice-cloning workflow, watermark integrity, abuse-detection (§24.7)
Voice provider/profile layer (libs/iris/voice): a provider registry, a
profile-registry, voice cloning workflow, and integrity tooling
(watermark.ts, abuse detection) — barrel re-exports
providers/cloning/integrity.
Web browsing tools for Iris AI agents - search, fetch, scrape, navigate, forms
Web browsing tools for agents: HttpClient, ContentParser, and
Search/Fetch/Scrape/ Navigate/Form tools with URL validation, composed as
WebTools.
createValidatedUrl159createSessionId159createRequestId159DEFAULT_WEB_TOOL_CONFIG159DEFAULT_SEARCH_TOOL_CONFIG159validateUrl171normalizeUrl171resolveUrl171getDomain171matchesDomain171checkDomain171xtractUrls171arseUrlComponents171buildUrl171 +25 moreinfra (1)#
Configuration management for the Iris AI Assistant framework
Configuration management: model-provider config (Anthropic/OpenAI/Google),
MemGPT-style hierarchical memory config, voice (STT/TTS/VAD) config, privacy
settings, and a feature-flag system with a loader.
ProviderAuthMethodSchema47BaseProviderConfigSchema47AnthropicProviderConfigSchema47OpenRouterProviderConfigSchema47OpenAIProviderConfigSchema47GoogleProviderConfigSchema47CohereProviderConfigSchema47MistralProviderConfigSchema47GroqProviderConfigSchema47AWSBedrockProviderConfigSchema47AzureOpenAIProviderConfigSchema47ReplicateProviderConfigSchema47TogetherProviderConfigSchema47LocalProviderConfigSchema47 +159 moretesting (1)#
Test utilities and mocks for Iris AI Assistant
The Iris test-utilities library (~30 modules): mock model/memory providers, fixtures, conversation/user factories, assertions, benchmarks, and API/event-contract + bias/ factuality/consistency/latency/load test helpers — the shared testing toolkit for the area.
createMockModelProvider42createEchoProvider42createFailingProvider42createFlakeyProvider42createSlowProvider42createStreamingProvider42createToolCallingProvider42generateMockId42ModelProvider42ModelCapability42MessageRole42ContentBlock42ChatMessage42MockResponseConfig42 +515 moreunclassified (186)#
accessibility-* (4)#
Adaptive UI engine with capability detection and preference sync
Adaptive-UI accessibility engine (adaptive-ui-engine.ts,
interface-adapter.ts, user-capability-detector.ts, preference-sync.ts)
that detects user capabilities and adapts the interface and syncs preferences.
Real implementation, ~8 modules.
DEFAULT_BASE_INTERFACE_STATE25DEFAULT_USER_CAPABILITY_DETECTOR_CONFIG25DEFAULT_INTERFACE_ADAPTER_CONFIG25DEFAULT_PREFERENCE_SYNC_CONFIG25UserCapabilityDetector32createUserCapabilityDetector32InterfaceAdapter37createInterfaceAdapter37PreferenceSync39createPreferenceSync39AdaptiveUIEngine42createAdaptiveUIEngine42Braille output, input, formatting, and display integration for accessibility
Braille support: BrailleFormatting, BrailleOutput, BrailleInput, and
braille-display-integration.ts for refreshable-display I/O and braille
translation.
DEFAULT_BRAILLE_OUTPUT_CONFIG31DEFAULT_BRAILLE_DISPLAY_CONFIG31DEFAULT_BRAILLE_INPUT_CONFIG31DEFAULT_BRAILLE_FORMATTING_CONFIG31BrailleFormatting38createBrailleFormatting38BrailleOutput40createBrailleOutput40BrailleDisplayIntegration42createBrailleDisplayIntegration42BrailleInput47createBrailleInput47Automated and manual accessibility testing toolkit
Accessibility test tooling: AutomatedA11yChecks, A11yReporter,
A11yTestSuite, and a manual-checklist generator for verifying a11y compliance.
DEFAULT_AUTOMATED_A11Y_CHECKS_CONFIG26DEFAULT_MANUAL_CHECKLIST_GENERATOR_CONFIG26DEFAULT_A11Y_REPORTER_CONFIG26AutomatedA11yChecks32createAutomatedA11yChecks32ManualChecklistGenerator34createManualChecklistGenerator34A11yReporter39createA11yReporter39A11yTestSuite42createA11yTestSuite42Voice-first accessibility interface framework with menus, navigation, and feedback
Voice-driven UI framework: VoiceNavigation, VoiceFeedback, voice-menus.ts,
composed by createVoiceUIFramework.
DEFAULT_VOICE_NAVIGATION_CONFIG35DEFAULT_VOICE_MENUS_CONFIG35DEFAULT_VOICE_FEEDBACK_CONFIG35DEFAULT_VOICE_UI_FRAMEWORK_CONFIG35VoiceNavigation42createVoiceNavigation42VoiceMenus44createVoiceMenus44createMenuActionResult44createStaticAction44createMenuId44VoiceFeedback52createVoiceFeedback52VoiceUIFramework55 +1 moreagent-* (3)#
Marketplace primitives for agent packages: AgentMarketplace, AgentPublisher,
AgentInstaller, AgentRating (publish/discover/install/rate).
AgentMarketplace26createAgentMarketplace26AgentPublisher28createAgentPublisher28AgentInstaller30createAgentInstaller30AgentRating32createAgentRating32Agent personality profiles: PersonalityTraits, CommunicationStyle
derivation, and observation-driven personality-evolution.ts.
DEFAULT_PERSONALITY_TRAITS29DEFAULT_COMMUNICATION_STYLE29DEFAULT_EVOLUTION_STATE29DEFAULT_AGENT_PERSONALITY_CONFIG29DEFAULT_PERSONALITY_EVOLUTION_CONFIG29PersonalityTraits37createPersonalityTraits37CommunicationStyle39createCommunicationStyle39AgentPersonality41createAgentPersonality41CreateAgentPersonalityInput41PersonalityEvolution47createPersonalityEvolution47 +1 moreDomain specialization for multi-agent systems:
domain-specialization-training.ts, SpecializationTransfer,
ExpertiseMapping, SpecializationMetrics.
DEFAULT_DOMAIN_SPECIALIZATION_TRAINING_CONFIG34DEFAULT_SPECIALIZATION_TRANSFER_CONFIG34DEFAULT_SPECIALIZATION_METRICS_CONFIG34DomainSpecializationTraining40createDomainSpecializationTraining40SpecializationTransfer45createSpecializationTransfer45ExpertiseMapping47createExpertiseMapping47SpecializationMetrics49createSpecializationMetrics49analytics-* (4)#
A/B test analytics toolkit for statistical experiment analysis
A/B-test analytics: VariantComparison, ABTestAnalyzer, ABTestReporter, and
a real statistical-significance.ts.
DEFAULT_STATISTICAL_SIGNIFICANCE_CONFIG28DEFAULT_VARIANT_COMPARISON_CONFIG28DEFAULT_AB_TEST_ANALYZER_CONFIG28DEFAULT_AB_TEST_REPORTER_CONFIG28StatisticalSignificance35createStatisticalSignificance35VariantComparison40createVariantComparison40ABTestAnalyzer42createABTestAnalyzer42ABTestReporter44createABTestReporter44Cohort analytics toolkit for retention and behavior comparison
Cohort analytics: CohortAnalyzer, RetentionAnalysis, BehaviorComparison,
CohortReporter.
DEFAULT_COHORT_ANALYZER_CONFIG25DEFAULT_RETENTION_ANALYSIS_CONFIG25DEFAULT_BEHAVIOR_COMPARISON_CONFIG25DEFAULT_COHORT_REPORTER_CONFIG25CohortAnalyzer32createCohortAnalyzer32RetentionAnalysis34createRetentionAnalysis34BehaviorComparison36createBehaviorComparison36CohortReporter38createCohortReporter38Funnel analytics toolkit for conversion and drop-off intelligence
Funnel analytics: FunnelAnalyzer, ConversionTracking, DropOffAnalysis,
FunnelVisualization.
DEFAULT_FUNNEL_ANALYZER_CONFIG37DEFAULT_CONVERSION_TRACKING_CONFIG37DEFAULT_DROP_OFF_ANALYSIS_CONFIG37DEFAULT_FUNNEL_VISUALIZATION_CONFIG37FunnelAnalyzer44createFunnelAnalyzer44ConversionTracking46createConversionTracking46DropOffAnalysis48createDropOffAnalysis48FunnelVisualization50createFunnelVisualization50Real-time analytics toolkit for Iris platform telemetry streams
Real-time analytics: LiveMetrics, StreamingAggregation, AlertingTriggers,
RealtimeDashboard.
DEFAULT_LIVE_METRICS_CONFIG26DEFAULT_STREAMING_AGGREGATION_CONFIG26DEFAULT_ALERTING_TRIGGERS_CONFIG26DEFAULT_REALTIME_DASHBOARD_CONFIG26LiveMetrics33createLiveMetrics33StreamingAggregation35createStreamingAggregation35AlertingTriggers37createAlertingTriggers37RealtimeDashboard39createRealtimeDashboard39bci-* (4)#
Brain-Computer Interface preparation layer for IRIS multimodal system
Brain-computer-interface preparation layer (libs/iris/multimodal/bci): device
abstraction, neural-signal processing, intent prediction, thought-action
mapping, composed as BCISystem, with frequency-band helpers and an
isBCIAvailable capability probe.
DEFAULT_BCI_SYSTEM_CONFIG117BCIDeviceDefinition123SimulatedBCIDevice123BCIDeviceManager123DEFAULT_CONNECTION_OPTIONS123DEFAULT_DEVICE_MANAGER_CONFIG123BCIDeviceDiscoveryContext123BCIDeviceDiscoveryProvider123DeviceConnectionOptions123DeviceManagerConfig123DeviceEvent123DeviceEventListener123createSimulatedDevice123getDeviceDefinition123 +61 moreApple BCI HID protocol support with intent decoding, thought-action mapping, and calibration flow
Apple BCI-over-HID integration: AppleBCIHIDListener, IntentSignalDecoder,
ThoughtToActionMapper, BCICalibrationFlow, composed as AppleBCIHIDEngine.
AppleBCIHIDListener5IntentSignalDecoder6ThoughtToActionMapper7BCICalibrationFlow8AppleBCIHIDEngine9DEFAULT_APPLE_BCI_HID_LISTENER_CONFIG11DEFAULT_INTENT_SIGNAL_DECODER_CONFIG11DEFAULT_THOUGHT_TO_ACTION_MAPPER_CONFIG11DEFAULT_BCI_CALIBRATION_FLOW_CONFIG11oAppleBCIDeviceId11oCalibrationSessionId11oAppleBCICalibrationProfileId11BCI intent prediction API with confidence scoring, ambiguity resolution, confirmation flow, and feedback learning
BCI intent prediction: IntentPredictionModel, ConfidenceScorerBCI,
AmbiguityResolver, confirmation flow, feedback loop, and a fromAppleBCIFrame
feature-vector adapter.
IntentPredictionModel5ConfidenceScorerBCI6AmbiguityResolver7IntentConfirmationFlow8BCIFeedbackLoop9IntentPredictionAPI10fromAppleBCIFrame11DEFAULT_INTENT_PREDICTION_MODEL_CONFIG13DEFAULT_CONFIDENCE_SCORER_BCI_CONFIG13DEFAULT_AMBIGUITY_RESOLVER_CONFIG13DEFAULT_INTENT_CONFIRMATION_FLOW_CONFIG13DEFAULT_BCI_FEEDBACK_LOOP_CONFIG13oConfirmationRequestId13Privacy and rights framework for BCI processing with minimization, consent, deletion, and auditing
Neural-data privacy: NeuralDataMinimization, MentalPrivacyProtection,
NeuralDataDeletion (+ in-memory store), BCIAuditTrail, cognitive-liberty
consent, and a BCIPrivacyFramework with ProtectedInferenceResult.
NeuralDataMinimization5MentalPrivacyProtection6CognitiveLibertyConsentFramework7ConsentCheck7NeuralDataDeletion11InMemoryNeuralDataStore11BCIAuditTrail12BCIPrivacyFramework13ProtectedInferenceResult13DEFAULT_NEURAL_DATA_MINIMIZATION_CONFIG15DEFAULT_MENTAL_PRIVACY_PROTECTION_CONFIG15DEFAULT_COGNITIVE_LIBERTY_CONSENT_CONFIG15oBCIUserId15oBCISessionId15 +2 morecode-* (20)#
Architecture intelligence for pattern detection, coupling analysis, and visual modeling
Architecture analysis: ArchitectureAnalyzer, PatternDetector,
CouplingAnalyzer, and ArchitectureVisualizer for structural artifacts.
DEFAULT_PATTERN_DETECTOR_CONFIG33DEFAULT_COUPLING_ANALYZER_CONFIG33DEFAULT_ARCHITECTURE_ANALYZER_CONFIG33normalizeFilePath39inferModuleName39xtractImportSpecifiers39specifierToModule39uniqueSorted39clamp39buildModuleFileMap39PatternDetector49createPatternDetector49CouplingAnalyzer51createCouplingAnalyzer51 +5 moreIris CLI coding assistant with git workflow, build automation, deployment assistance, and log analysis
CLI coding assistant (~25 modules): a bin.ts entry, cli-assistant, git
workflow (PRGenerator, ReviewAnalyzer, commit-generator,
conflict-resolver), build/deploy assistance, log analysis, and createCLI.
CLIAssistant15createAssistant15AssistantOptions15ChatOptions15ChatResult15SlashCommand15ContextManager24ContextItem24ContextSnapshot24PromptBuilder26PromptTemplate26BuiltPrompt26GitWorkflow29createGitWorkflow29 +29 moreCodebase understanding and repository analysis for Iris code intelligence
Codebase analysis: RepoAnalyzer, ArchitectureInference,
DependencyAnalyzer, PatternDetector, and CodebaseIndexer/CodebaseSearch,
composed as CodebaseAnalyzer.
CodebaseAnalyzer10RepoAnalyzer13ArchitectureInference14DependencyAnalyzer15PatternDetector16CodebaseIndexer17CodebaseSearch17DEFAULT_CODEBASE_ANALYZER_CONFIG79Code consistency checking for style, naming, patterns, and API consistency
Code-consistency checking: StyleConsistencyChecker,
NamingConventionEnforcer, PatternChecker, APIConsistencyChecker with
quick-scan helpers and a combined analyzer.
StyleConsistencyChecker33createStyleChecker33quickStyleScan33NamingConventionEnforcer36createNamingEnforcer36quickNamingScan36PatternConsistencyChecker39createPatternChecker39quickPatternScan39APIConsistencyChecker46createAPIChecker46quickAPIScan46CodeConsistencyAnalyzer69createConsistencyAnalyzer304 +1 moreDependency intelligence for analysis, vulnerability scanning, update planning, and license compliance
Dependency intelligence: declaration analysis, VulnerabilityScanner,
UpdateSuggester, LicenseChecker (license-policy validation).
DEFAULT_DEPENDENCY_ANALYZER_CONFIG35DEFAULT_UPDATE_SUGGESTER_CONFIG35DEFAULT_LICENSE_POLICY35normalizeVersion41arseSemver41compareSemver41isVersionBelow41classifyUpdateStrategy41bumpPatch41normalizePackageSpecifier41isBuiltinModule41xtractImportedPackages41DependencyAnalyzer53createDependencyAnalyzer53 +7 moreCode explanation and understanding tools
Educational code explanation: CodeExplainer, step walkthroughs,
ConceptExtractor, DiagramGenerator.
CodeExplainer61createCodeExplainer61CodeExplainerOptions61StepByStepWalkthrough67createStepWalkthrough67WalkthroughGeneratorOptions67ConceptExtractor77createConceptExtractor77ConceptExtractorOptions77DiagramGenerator83createDiagramGenerator83DiagramGeneratorOptions83Deep git integration utilities for commit messages, PR descriptions, branch naming, and conflict resolution
Deep git integration (~21 modules): diff parsing, commit-message/PR generation,
branch-name suggestion, deterministic conflict-resolver, style enforcement,
repo indexing, and a technical-debt tracker.
DEFAULT_COMMIT_MESSAGE_OPTIONS104DEFAULT_COMMIT_MESSAGE_ASSISTANT_CONFIG104DEFAULT_PR_DESCRIPTION_OPTIONS104DEFAULT_BRANCH_NAME_OPTIONS104DEFAULT_CONFLICT_RESOLVER_OPTIONS104DEFAULT_GIT_INTEGRATION_CONFIG104DEFAULT_GIT_REPOSITORY_INDEXER_CONFIG104DEFAULT_CODEBASE_CONTEXT_INJECTOR_CONFIG104DEFAULT_CODE_DIFF_GENERATOR_CONFIG104DEFAULT_PR_REVIEW_ASSISTANCE_CONFIG104DEFAULT_CODE_REFACTORING_SUGGESTER_CONFIG104DEFAULT_CODE_DOCUMENTATION_GENERATOR_CONFIG104DEFAULT_CODE_MIGRATION_ASSISTANT_CONFIG104DEFAULT_CODE_SECURITY_SCANNING_INTEGRATION_CONFIG104 +48 moreIDE integration layer for AI code assistance - supports VSCode, JetBrains, Neovim, and Emacs
IDE integration layer: a BaseIDEAdapter with concrete
VSCode/JetBrains/Neovim/Emacs adapters, JSON-RPC,
inline-suggestions/chat/code-action services, plus detectIDEEnvironment and
createAutoDetectedAdapter.
BaseIDEAdapter43DisposableCollection43JsonRpcConnection49JsonRpcException49InMemoryTransport49WebSocketTransport49HttpTransport49createTestConnection49createWebSocketConnection49createHttpConnection49Transport49RequestHandler49NotificationHandler49StreamHandler49 +71 moreAI-powered IDE code actions for fixes, refactors, and generation workflows
IDE code actions: CodeActionProvider, FixActions, RefactorActions,
GenerateActions.
DEFAULT_FIX_ACTIONS_CONFIG26DEFAULT_REFACTOR_ACTIONS_CONFIG26DEFAULT_GENERATE_ACTIONS_CONFIG26DEFAULT_CODE_ACTION_PROVIDER_CONFIG26stableId33clamp33selectedOrNearbyText33countLines33summarizeLanguage33sortActions33dedupeActions33classifySeverityBoost33FixActions44createFixActions44 +7 moreSmart code completion engine for context-aware and multi-line IDE suggestions
Smart completions: context-aware and multi-line completions, completion
explanation, and a SmartCompletionProvider.
DEFAULT_CONTEXT_AWARE_COMPLETIONS_CONFIG32DEFAULT_MULTI_LINE_COMPLETIONS_CONFIG32DEFAULT_COMPLETION_EXPLANATION_CONFIG32DEFAULT_SMART_COMPLETION_PROVIDER_CONFIG32stableId39clamp39currentLine39xtractPrefix39isSubsequenceMatch39detectIndentation39nextIndentUnit39completionPrefixScore39scoreConfidence39ContextAwareCompletions51 +8 moreSmart IDE hover information with docs, types, and contextual explanations
Editor hover: DocumentationHover, TypeHover, ExplanationHover, and a
SmartHoverProvider.
DEFAULT_DOCUMENTATION_HOVER_CONFIG27DEFAULT_TYPE_HOVER_CONFIG27DEFAULT_EXPLANATION_HOVER_CONFIG27DEFAULT_SMART_HOVER_PROVIDER_CONFIG27clamp34hoveredOrToken34nearbyCode34findJsDoc34inferLiteralType34countLines34summarizeLanguage34DocumentationHover44createDocumentationHover44TypeHover46 +6 moreInline chat UX primitives for in-editor AI conversations
In-editor inline chat: ContextualSuggestions, QuickActions,
InlineExplanation, and an inline-chat-widget.
DEFAULT_CONTEXTUAL_SUGGESTIONS_CONFIG33DEFAULT_QUICK_ACTIONS_CONFIG33DEFAULT_INLINE_EXPLANATION_CONFIG33DEFAULT_INLINE_CHAT_WIDGET_CONFIG33stableId40clamp40selectedOrNearbyText40countLines40summarizeLanguage40ContextualSuggestions42createContextualSuggestions42QuickActions44createQuickActions44InlineExplanation46 +4 moreLanguage-specific code analyzers for major programming languages
Per-language analyzers extending code-understanding — TypeScript, Python, Java,
Go, Rust, C++, SQL, GraphQL — selected via
createLanguageAnalyzer/hasLanguageAnalyzer.
BaseLanguageAnalyzer35PatternMatcher35FrameworkDetector35InsightGenerator35SingletonPatternMatcher35FactoryPatternMatcher35ObserverPatternMatcher35TypeScriptAnalyzer46PythonAnalyzer46RustAnalyzer46GoAnalyzer46JavaAnalyzer46CPPAnalyzer46SQLAnalyzer46 +4 morePersistent coding memory with style profiling, preference inference, project context persistence, and convention enforcement
Coding-style memory: PreferenceInferrer, CodingStyleMemory (+ in-memory
store), CodeConventionEnforcer, project-context persistence, composed as
CodingMemoryPersistenceEngine.
PreferenceInferrer5CodingStyleMemory6InMemoryCodingStyleMemoryStore6ProjectContextPersistence7InMemoryProjectContextPersistenceStore7CodeConventionEnforcer11CodingMemoryPersistenceEngine12DEFAULT_CODING_STYLE_MEMORY_CONFIG14DEFAULT_PROJECT_CONTEXT_PERSISTENCE_CONFIG14oRepositoryId14oProjectSessionId14Code quality metrics including complexity, maintainability, and technical debt scoring
Code metrics: CodeMetricsCollector, ComplexityScorer,
MaintainabilityScorer, technical-debt-calculator.
DEFAULT_CODE_METRICS_COLLECTOR_CONFIG29DEFAULT_COMPLEXITY_SCORER_CONFIG29DEFAULT_MAINTAINABILITY_SCORER_CONFIG29DEFAULT_TECHNICAL_DEBT_CALCULATOR_CONFIG29inferLanguage36average36clamp36stableId36countMaxNestingDepth36countBranchingStatements36stimateFunctionLengths36CodeMetricsCollector46createCodeMetricsCollector46ComplexityScorer48 +5 moreCode-quality analysis: SecurityVulnerabilityDetector, PerformanceOptimizer,
BestPracticeEnforcer, TechnicalDebtIdentifier, CodeReviewer, plus
quick-scan helpers and a combined QualityAnalyzer.
SeveritySchema74IssueCategorySchema74SourceLocationSchema74FixChangeSchema74CodeFixSchema74QualityIssueSchema74QualityScoreSchema74VulnerabilityTypeSchema74PerformanceIssueTypeSchema74BestPracticeTypeSchema74DebtTypeSchema74ReviewCommentTypeSchema74DEFAULT_QUALITY_CONFIG93DEFAULT_SECURITY_CONFIG93 +23 moreRepository-scale code understanding with indexing, dependency graphing, architecture inference, and multi-file reasoning
Repository intelligence: RepositoryIndexer, DependencyGraphBuilder,
ArchitectureInferrer, ConventionDetector, MultiFileReasoner, composed as
RepositoryIntelligenceEngine.
RepositoryIndexer5DependencyGraphBuilder6ArchitectureInferrer7ConventionDetector8MultiFileReasoner9RepositoryIntelligenceEngine10DEFAULT_REPOSITORY_INDEXER_CONFIG12DEFAULT_DEPENDENCY_GRAPH_BUILDER_CONFIG12Automated code review assistant with diff analysis, issue detection, and actionable suggestions
Automated code-review pipeline: DiffAnalyzer, IssueDetector,
SuggestionGenerator, ReviewCommentFormatter, composed as
CodeReviewAssistant.
DEFAULT_DIFF_ANALYZER_CONFIG35DEFAULT_ISSUE_DETECTOR_CONFIG35DEFAULT_SUGGESTION_GENERATOR_CONFIG35DEFAULT_REVIEW_COMMENT_FORMATTER_CONFIG35DEFAULT_REVIEW_ASSISTANT_CONFIG35DiffAnalyzer43createDiffAnalyzer43IssueDetector44createIssueDetector44SuggestionGenerator45createSuggestionGenerator45ReviewCommentFormatter46createReviewCommentFormatter46CodeReviewAssistant50 +2 moreIris code search - semantic search, symbol lookup, usage finding, and pattern matching
Code search: SemanticCodeSearch, symbol search, UsageSearch,
SimilarCodeSearch, and a UnifiedCodeSearch composer.
SemanticCodeSearch12createSemanticSearch12SemanticSearcherOptions12SymbolSearch15createSymbolSearch15SymbolSearcherOptions15SymbolHierarchy15UsageSearch23createUsageSearch23UsageSearcherOptions23SimilarCodeSearch26createSimilarSearch26SimilarSearcherOptions26UnifiedSearchOptions31 +2 moreAutonomous terminal execution with safety validation, permission gating, failure interpretation, and iterative fixes
Autonomous terminal execution: CommandSafetyValidator,
AutonomousTerminalExecutor, ExecutionResultInterpreter, an
IterativeFixLoop, and a turbo-mode permission manager.
CommandSafetyValidator5AutonomousTerminalExecutor6NodeProcessCommandRunner6DEFAULT_NODE_PROCESS_COMMAND_RUNNER_CONFIG6ExecutionResultInterpreter11IterativeFixLoop12DEFAULT_ITERATIVE_FIX_STRATEGIES12TurboModePermissionManager13DEFAULT_COMMAND_SAFETY_VALIDATOR_CONFIG15DEFAULT_TURBO_MODE_PERMISSION_CONFIG15DEFAULT_AUTONOMOUS_EXECUTOR_CONFIG15DEFAULT_ITERATIVE_FIX_LOOP_CONFIG15computer-* (5)#
Computer use agent for GUI automation with screen capture, action execution, and element detection
Computer-use GUI-automation agent: ScreenCapture, ActionExecutor, element
detection, and createComputerUseAgent. The directory also nests the Rust
native/ backend.
ActionId14ElementId14ComputerSessionId14createActionId14createElementId14createComputerSessionId14ColorDepth14CaptureRegion14CaptureOptions14CaptureResult14CaptureSession14ScreenCaptureConfig14DEFAULT_SCREEN_CAPTURE_CONFIG14ModifierKey14 +61 moreAccessibility-first automation primitives: SemanticUINavigation,
A11yTreeInspector, robust-element-selection.ts,
accessibility-api-integration.ts for tree-aware desktop control.
DEFAULT_ACCESSIBILITY_INTEGRATION_CONFIG26DEFAULT_ROBUST_SELECTION_CONFIG26AccessibilityAPIIntegration31createAccessibilityAPIIntegration31SemanticUINavigation36createSemanticUINavigation36A11yTreeInspector38createA11yTreeInspector38RobustElementSelection40createRobustElementSelection40Task recording for computer-use workflows: ScreenRecorder, ActionAnnotator,
RecordingPlayback, RecordingExport.
DEFAULT_SCREEN_RECORDER_CONFIG19DEFAULT_PLAYBACK_OPTIONS19ScreenRecorder21createScreenRecorder21ActionAnnotator23createActionAnnotator23RecordingPlayback25createRecordingPlayback25RecordingExport27createRecordingExport27Graceful error recovery for automation: ErrorDetector, recovery-strategy
selection, RollbackManager, AlternativePathFinder, orchestrated by
RecoveryManager.
DEFAULT_ERROR_DETECTOR_CONFIG34DEFAULT_RECOVERY_CONTEXT34ErrorDetector36createErrorDetector36RecoveryStrategySelector38createRecoveryStrategySelector38RollbackManager43createRollbackManager43AlternativePathFinder45createAlternativePathFinder45RecoveryManager47createRecoveryManager47Reusable computer-use task templates: builder, parameterization, sharing, and a
TemplateLibrary for lifecycle management.
DEFAULT_TASK_TEMPLATE_EXECUTION40DEFAULT_PARAMETERIZATION_OPTIONS40DEFAULT_TEMPLATE_SHARING40TaskTemplateBuilder46createTaskTemplateBuilder46createTaskTemplateBuilderFromTask46TemplateParameterization52createTemplateParameterization52TemplateSharing57createTemplateSharing57TemplateLibrary59createTemplateLibrary59conversation-* (19)#
Model benchmarking: latency/quality/cost benchmarks and a BenchmarkSuite (with
a mock model invoker) plus a reporter.
BenchmarkRunId9TestCaseId9createBenchmarkRunId9createTestCaseId9BenchmarkStatus9ModelConfig9TestCase9TestCaseResult9TTFTStats9LatencyBenchmarkResult9QualityMetric9QualityScoreBreakdown9QualityBenchmarkResult9CostBenchmarkResult9 +32 moreCitation and attribution system for Iris conversational AI - source tracking, inline citations, reference formatting, and fact checking
Citation/attribution: CitationTracker, SourceAttributor,
ReferenceFormatter, FactChecker for inline citations and source tracking.
createSourceId92createClaimId92DEFAULT_REFERENCE_FORMATTER_CONFIG92DEFAULT_SOURCE_ATTRIBUTOR_CONFIG92DEFAULT_FACT_CHECKER_CONFIG92CitationTracker112createCitationTracker112createDefaultCitationTracker112createMinimalCitationTracker112createAcademicCitationTracker112rackSourcesFromData112TrackerStatistics112SourceData112ReferenceFormatter127 +25 moreLLM cost tracking: CostTracker, BudgetManager, CostAlerting,
CostReporting.
createCostTrackingId68createBudgetId68createAlertId68createReportId68createUserId68createOrganizationId68CostTracker78BudgetManager81CostAlerting84AlertHandler84CostReporting87Export conversations in multiple formats (Markdown, PDF, JSON, HTML)
Conversation export: Markdown/HTML/JSON/PDF exporters composed as
ConversationExporter.
MessageId13ConversationId13createMessageId13createConversationId13ConversationMessage13Conversation13Attachment13ExportStatus13ExportResult13MarkdownExportOptions13HTMLExportOptions13JSONExportOptions13PDFExportOptions13TextExportOptions13 +31 moreModel fine-tuning infrastructure for custom model training and management
Fine-tuning infrastructure: DataCollector, JobManager,
ModelVersionManager, finetuning-metrics.
JobId10ModelId10ModelVersionId10TrainingExampleId10createJobId10createModelId10createModelVersionId10createTrainingExampleId10TrainingMessage10TrainingExample10TrainingDataset10DatasetStats10BaseModel10HyperParameters10 +25 moreMulti-format response formatting system for Iris conversational AI with specialized formatters for text, markdown, code, structured data, and media
Multi-format response formatting: text, markdown, code, structured-data, and media formatters.
createMediaId91DEFAULT_TEXT_OPTIONS91DEFAULT_MARKDOWN_OPTIONS91DEFAULT_CODE_OPTIONS91DEFAULT_STRUCTURED_DATA_OPTIONS91DEFAULT_MEDIA_OPTIONS91TextFormatter112createTextFormatter112formatText112wrapText112normalizeWhitespace112getTextStats112capitalizeText112MarkdownFormatter126 +33 moreModel orchestration layer for Iris conversational AI - provider routing, load balancing, circuit breaking, and rate limiting
Provider-agnostic model orchestration: ModelOrchestrator, RequestRouter,
LoadBalancer, CircuitBreaker, RateLimiter, and a ModelRegistry with
retries/ fallbacks/metrics.
createRequestId135createCircuitBreakerId135createDefaultRateLimiterConfig135createDefaultLoadBalancerConfig135createDefaultFallbackConfig135createDefaultRetryConfig135createDefaultModelOrchestratorConfig135CircuitBreaker154CircuitBreakerOpenError154CircuitBreakerRegistry154createCircuitBreaker154createStrictCircuitBreaker154createLenientCircuitBreaker154createCircuitBreakerRegistry154 +59 morePrompt management: PromptLibrary, PromptVersioning, PromptTesting (with
calculateSampleSize), PromptOptimizer.
PromptVersionId9PromptTestId9PromptVariantId9createPromptVersionId9createPromptTestId9createPromptVariantId9PromptVariable9PromptSection9PromptCategory9PromptTemplate9RenderedPrompt9PromptVersion9VersionMetrics9VersionDiff9 +23 moreAnthropic Claude provider integration for Iris conversation system
Anthropic Claude provider adapter (anthropic-provider.ts +
orchestration-adapter.ts): chat/streaming/tool-use/vision/extended-thinking
support and a default-config factory, plugging into the orchestrator.
createDefaultAnthropicConfig62AnthropicProvider68AnthropicProviderError68createAnthropicProvider68getAnthropicModels68AnthropicOrchestrationAdapter81createAnthropicOrchestrationAdapter81createAnthropicExecutor81createAnthropicStreamingExecutor81getAnthropicModelsForOrchestration81Google Gemini provider integration for Iris conversation system
Google Gemini provider adapter: chat with system instructions, multimodal inputs, function calling, streaming, and an orchestration adapter.
GoogleProvider38GoogleProviderError38createGoogleProvider38getGoogleModels38getGoogleModel38GoogleOrchestrationAdapter47createGoogleOrchestrationAdapter47createGoogleExecutor47createGoogleStreamingExecutor47getGoogleModelsForOrchestration47GoogleAdapterConfig47MessageConversionOptions47createDefaultGoogleConfig107Local model provider integration for Iris conversation system (Ollama, vLLM, llama.cpp)
Local-model provider adapter: an Ollama backend (ollama-provider.ts) for
Llama/Mistral/ DeepSeek/Qwen with tool-calling, streaming, and model management.
OllamaProvider36OllamaProviderError36createOllamaProvider36getOllamaModels36getOllamaModel36LocalOrchestrationAdapter45createLocalOrchestrationAdapter45createLocalExecutor45createLocalStreamingExecutor45getLocalModelsForOrchestration45LocalAdapterConfig45createDefaultOllamaConfig104createDefaultVLLMConfig104createDefaultLlamaCppConfig104OpenAI provider integration for Iris conversation system
OpenAI provider adapter: chat/streaming/embeddings/moderation plus an orchestration adapter and default-config factory.
createDefaultOpenAIConfig70OpenAIProvider76OpenAIProviderError76createOpenAIProvider76createAzureOpenAIProvider76getOpenAIModels76getOpenAIEmbeddingModels76OpenAIOrchestrationAdapter91createOpenAIOrchestrationAdapter91createOpenAIExecutor91createOpenAIStreamingExecutor91getOpenAIModelsForOrchestration91RAG integration for conversation response generation with context injection, source tracking, and fallback strategies
RAG integration for response generation: RAGPipeline with ContextInjector,
SourceTracker, RelevanceScorer, and RAGFallback (plus a high-quality
preset).
InjectionId50SourceTrackingId50createRAGPipelineId50createInjectionId50createSourceTrackingId50RAGPipelineStatus50QueryAnalysis50ExtractedEntity50QueryIntent50RAGPipelineConfig50QueryAnalysisConfig50RetrievalConfig50RelevanceScoringConfig50ContextInjectionConfig50 +70 moreResponse generation pipeline for conversational AI with streaming, validation, and multi-format support
Response-generation pipeline: ResponseGenerator, PromptBuilder,
ResponseParser, ResponseValidator, ResponseFormatter, and streaming
response support.
ChunkId37createResponseId37createChunkId37ResponseFormat37ResponsePriority37ResponseConfig37DEFAULT_RESPONSE_CONFIG37PipelineStageStatus37StageResult37PipelineState37PromptSection37BuiltPrompt37PromptMessage37StreamChunk37 +79 moreComprehensive conversation search with full-text, semantic, and filtered search capabilities
Conversation search: full-text ConversationSearch, semantic/vector search,
filters, and a highlighter.
SearchResultId14MessageId14ConversationId14IndexId14createSearchResultId14createMessageId14createConversationId14createIndexId14ConversationMessage14Conversation14MatchType14SearchScope14SortOrder14SearchQuery14 +33 moreAdvanced state management for dialogue systems with guards, rollback, and branching
Advanced dialogue-state management: guard-evaluated state machines,
CheckpointManager (persistence/recovery), BranchManager (exploration),
composed as StateManager.
createCheckpointId97createBranchId97DEFAULT_STATE_MANAGER_CONFIG97GuardEvaluator100createGuardEvaluator100createTruthyGuard100createFromStateGuard100createNotToStateGuard100createAndGuard100createOrGuard100createNotGuard100CheckpointManager114createCheckpointManager114BranchManager117 +3 moreStyle adaptation system for Iris AI assistant - tone detection, formality control, personality matching, and style learning
Style adaptation: ToneDetector, FormalityController, PersonalityMatcher,
StyleLearner, composed as StyleAdapter.
createStyleSessionId127DEFAULT_SPEECH_PATTERN127DEFAULT_TONE_DETECTOR_CONFIG127DEFAULT_FORMALITY_CONTROLLER_CONFIG127DEFAULT_STYLE_LEARNER_CONFIG127ToneDetector144createToneDetector144createSensitiveToneDetector144createProfessionalToneDetector144FormalityController155createFormalityController155createStrictFormalityController155createBusinessFormalityController155PersonalityMatcher166 +16 moreToken optimization: TokenCounter/SimpleTokenizer, TokenOptimizer,
ContextCompressor, TokenBudgetManager.
createTokenCount64createTokenBudgetId64createCompressionSessionId64TokenCounter67SimpleTokenizer67TokenOptimizer70ContextCompressor73TokenBudgetManager76Uncertainty quantification system for Iris conversational AI - confidence estimation, hedging language, clarification generation, and knowledge boundary detection
Uncertainty quantification: ConfidenceEstimator, UncertaintyExpressor
(hedging), ClarificationGenerator, KnowledgeBoundary detection.
createConfidenceId118createClaimId118createClarificationId118createDefaultCalibrationConfig118createDefaultConfidenceEstimatorConfig118createDefaultUncertaintyExpressorConfig118createDefaultClarificationGeneratorConfig118createDefaultKnowledgeBoundaryDetectorConfig118ConfidenceEstimator133createConfidenceEstimator133createConservativeEstimator133createPermissiveEstimator133quickAssess133UncertaintyExpressor145 +15 moreemotional-* (9)#
Advanced multimodal emotion fusion with text/voice analysis, contextual interpretation, and longitudinal tracking
Multimodal emotion fusion: TextEmotionAnalyzer, VoiceEmotionAnalyzer,
EmotionFusionEngine, ContextualEmotionInterpreter, EmotionHistoryTracker,
composed as MultimodalEmotionAnalyzer.
TextEmotionAnalyzer5VoiceEmotionAnalyzer6createSyntheticVoiceFrames6EmotionFusionEngine7ContextualEmotionInterpreter8EmotionHistoryTracker9MultimodalEmotionAnalyzer10DEFAULT_EMOTION_FUSION_CONFIG12DEFAULT_EMOTION_HISTORY_TRACKER_CONFIG12Multi-modal emotion recognition system with text sentiment analysis, voice emotion detection, and multimodal fusion
Multi-modal emotion recognition: EmotionRecognizer, TextSentimentAnalyzer,
VoiceEmotionAnalyzer, MultimodalFusion.
EmotionRecognizer14TextSentimentAnalyzer15VoiceEmotionAnalyzer16MultimodalFusion17BASIC_EMOTIONS160EXTENDED_EMOTIONS160EMOTION_DIMENSIONS160INTENSITY_THRESHOLDS160CONFIDENCE_THRESHOLDS160createEmotionalStateId172createEmotionSessionId172intensityToValue172valueToConfidenceLevel172scoreToPolarity172 +21 more48-category affective voice emotion analysis with prosodic modeling and temporal micro-shift detection
Prosody-based voice emotion analysis: ProsodEmotionAnalyzer, a 48-class
Emotion48Classifier, confidence/temporal tracking, micro-emotion detection,
composed as VoiceEmotionAnalysisEngine.
ProsodEmotionAnalyzer5Emotion48Classifier6EmotionConfidenceScorer7EmotionTemporalTracker8MicroEmotionDetector9VoiceEmotionAnalysisEngine10HUME_48_EMOTIONS12DEFAULT_PROSODIC_ANALYSIS_CONFIG12DEFAULT_CLASSIFIER_CONFIG12DEFAULT_CONFIDENCE_SCORER_CONFIG12DEFAULT_TEMPORAL_TRACKER_CONFIG12DEFAULT_MICRO_EMOTION_DETECTOR_CONFIG12DEFAULT_VOICE_EMOTION_ANALYSIS_CONFIG12Ethical boundaries for emotionally-aware AI - identity clarity, relationship respect, transparency, and crisis protocols
Non-negotiable ethical boundaries for emotionally-aware AI: AIIdentityClarity,
CapabilityTransparency, CrisisProtocol, MandatoryReferral,
human-relationship respect, composed as EthicalBoundaries. (Project name lacks
the @ prefix.)
DEFAULT_ETHICS_CONFIG74AIIdentityClarity77createAIIdentityClarity77HumanRelationshipRespect80createHumanRelationshipRespect80CapabilityTransparency86createCapabilityTransparency86CrisisProtocol89createCrisisProtocol89MandatoryReferral92createMandatoryReferral92EthicalBoundaries95createEthicalBoundaries95Rapport building and relationship management for emotionally-aware AI
Rapport building: TrustIndicators, RelationshipProgress, personalized
interaction, composed as RapportBuilder. (Name lacks @ prefix.)
DEFAULT_RAPPORT_CONFIG112DEFAULT_TRUST_CONFIG112DEFAULT_PERSONALIZATION_CONFIG112TrustIndicators119createTrustIndicators119RelationshipProgress122createRelationshipProgress122PersonalizedInteraction125createPersonalizedInteraction125RapportBuilder131createRapportBuilder131Emotionally adaptive response generation for Iris
Emotionally-adaptive response generation (~16 modules): EmotionalAdapter,
ToneMatcher, DeEscalator, Celebrator, Supporter, plus
crisis-support/stress-management/mindfulness/ gratitude-journal/wellbeing-report
modules with named default configs. (Name lacks @.)
DEFAULT_EMOTIONAL_ADAPTER_CONFIG123DEFAULT_RESPONSE_CALIBRATION_CONFIG124DEFAULT_CRISIS_SUPPORT_CONFIG125DEFAULT_GRATITUDE_JOURNAL_CONFIG126DEFAULT_STRESS_MANAGEMENT_CONFIG127DEFAULT_MINDFULNESS_GUIDANCE_CONFIG128DEFAULT_EMOTIONAL_PATTERN_INSIGHTS_CONFIG129DEFAULT_EMOTIONAL_WELLBEING_REPORT_CONFIG130EmotionalAdapter136createEmotionalAdapter136ToneMatcher142createToneMatcher142NEUTRAL_TONE142DeEscalator148 +23 moreSocial intelligence library for culturally aware, socially appropriate AI interactions
Social intelligence: CulturalAwareness, FormalityCalibrator,
HumorCalibrator, BoundaryRespect, SocialCueDetector, composed as
SocialIntelligence. (Name lacks @.)
DEFAULT_SOCIAL_INTELLIGENCE_CONFIG72CulturalAwareness78createCulturalAwareness78FormalityCalibrator84createFormalityCalibrator84HumorCalibrator90createHumorCalibrator90BoundaryRespect96createBoundaryRespect96SocialCueDetector102createSocialCueDetector102SocialIntelligence108createSocialIntelligence108Longitudinal emotion tracking and pattern analysis
Longitudinal emotion tracking: MoodTracker, PatternAnalyzer, TrendAnalyzer
over time. (Name lacks @ prefix.)
DEFAULT_MOOD_TRACKER_CONFIG83DEFAULT_TRACKING_PREFERENCES83DEFAULT_MOOD_TRACKING_CONSENT83MoodTracker93createMoodTracker93PatternAnalyzer99createPatternAnalyzer99DEFAULT_PATTERN_ANALYZER_CONFIG99TrendAnalyzer111createTrendAnalyzer111DEFAULT_TREND_ANALYZER_CONFIG111Consent-based wellbeing monitoring for emotionally-aware AI
Consent-based, explicitly non-diagnostic wellbeing monitoring: GentleCheckIn,
ResourceSuggester, ConcerningPatternDetector, ProfessionalReferral,
composed as WellbeingMonitor. (Name lacks @ prefix.)
DEFAULT_WELLBEING_CONSENT96DEFAULT_WELLBEING_CONFIG96ConcerningPatternDetector99createConcerningPatternDetector99GentleCheckIn105createGentleCheckIn105ResourceSuggester108createResourceSuggester108ProfessionalReferralAwareness111createProfessionalReferralAwareness111WellbeingMonitor117createWellbeingMonitor117integrations-* (6)#
Hathor Worldbuilding integration for Iris AI Platform
Integration adapter to the Hathor worldbuilding domain: lore context,
WorldKnowledgeService, CharacterDatabaseService,
TimelineNavigationService, LoreConsistencyChecker, plus
lore-keeper/plot-advisor/world-consistency agents (~22 modules).
WorldDateSchema81LoreQuerySchema81HathorIntegrationConfigSchema81LoreContextManager87createLoreContextManager87HathorClientLoreService87InMemoryHathorLoreService87createHathorClientLoreService87createInMemoryHathorLoreService87WorldKnowledgeService111createWorldKnowledgeService111CharacterDatabaseService124createCharacterDatabaseService124TimelineNavigationService132 +6 moreIris AI integration with Maya metaverse engine
Integration to the Maya metaverse engine: in-world MayaCompanion,
WorldContextManager, SpatialVoiceChat, WorldCommands, plus
world-builder/npc-control/asset-creator agents and personality presets.
Vector3Schema83QuaternionSchema83CompanionPersonalityTraitsSchema83CompanionConfigSchema83WorldContextManager94SpatialVoiceChat106WorldCommands119MayaCompanion132NPCControlAgent143AssetCreatorAgent143ScriptingAssistant143createNPCControlAgent143createAssetCreatorAgent143createScriptingAssistant143 +7 moreNyx Astronomy integration for Iris AI Platform
Integration to the Nyx astronomy domain: celestial-guide/event/educational
services and stargazer/observation-planner/astronomy-tutor agents, composed by
createNyxIntegration.
CelestialObjectTypeSchema71ObservationDifficultySchema71CelestialEventTypeSchema71EventSignificanceSchema71ContentDifficultySchema71AstronomyTopicSchema71GeographicLocationSchema71EquatorialCoordinatesSchema71CelestialGuideService86createCelestialGuideService86CelestialGuideEvents86ObjectSearchParams86ObjectSearchResult86ConstellationInfo86 +46 moreIris integration with Psyche domain for AI avatar representation, emotion expression, and conferencing presence
Integration to the Psyche domain for AI-avatar presence:
avatar/conferencing/emotion services and presenter/participant/persona agents
with a platform-adapter.
AvatarQualitySchema105PrimaryEmotionSchema105ExtendedEmotionSchema105ConferencePlatformSchema105ConnectionStateSchema105VideoInjectionModeSchema105AudioMixingModeSchema105CircumplexPositionSchema105RenderResolutionSchema105AvatarConfigSchema105ConferenceConfigSchema105AvatarService125AvatarServiceConfig125AvatarServiceEvents125 +62 moreSophia Research & Knowledge integration for Iris AI Platform
Integration to the Sophia research/knowledge domain: research-assistant,
knowledge-base, literature-search, and citation-manager services + agents,
composed by createSophiaIntegration.
DocumentTypeSchema83DocumentStatusSchema83CitationStyleSchema83VerificationStatusSchema83EntityTypeSchema83RelationTypeSchema83SearchModeSchema83KnowledgePackCategorySchema83AuthorSchema83SearchFilterSchema83SearchQuerySchema83RAGRequestSchema83ResearchAssistantService102ResearchAssistantConfig102 +85 moreIris AI Platform integration with Yemaya Creative Studio
Integration to the Yemaya creative-studio domain (~27 modules): project-context, asset-understanding, creative-suggestions, and workflow-automation services + agents (asset- organizer/audio-mixer/video-editor/design-assistant).
Vec3Schema113ProjectSettingsSchema113AssistantPersonalitySchema113AssistantCapabilitiesSchema113CreativeAssistantConfigSchema113ProjectContextManager125DCCProjectContextResolver125YemayaSDKProjectContextSource125createDCCProjectContextResolver125createYemayaSDKProjectContextSource125AssetUnderstandingService151CreativeSuggestionsEngine180WorkflowAutomationService194CreativeAssistant213 +14 moreknowledge-* (21)#
Iris Knowledge System - Unified knowledge management with source registry, indexing, freshness, and quality scoring
The unified knowledge system (libs/iris/knowledge/core, ~18 modules): source
registry, indexing, quality/freshness scoring, conflict detection, citation
formatting, federation, marketplace/monetization, and source-credibility
ranking, with capability probes (isKnowledgeAvailable).
createKnowledgeId114createSourceId114createChunkId114createIndexEntryId114createQueryId114createCollectionId114createKnowledgeError127DEFAULT_KNOWLEDGE_SYSTEM_CONFIG133SourceConfigSchema139SearchQuerySchema139KnowledgeItemSchema139SourceRegistryConfig145SourceItem145createSimulatedConnector145 +135 moreAgentic retrieval orchestration for autonomous strategy adaptation in Iris RAG
Agentic retrieval orchestration: QueryDecomposer, RetrievalStrategySelector,
IterativeRefinement, SourceQualityAssessor, dense/sparse/graph retrievers +
fusion + evaluator, plus an EmbeddingDenseRetriever, composed as
RetrievalAgent.
DEFAULT_RETRIEVAL_AGENT_CONFIG48DEFAULT_QUERY_DECOMPOSER_CONFIG48DEFAULT_ITERATIVE_REFINEMENT_CONFIG48DEFAULT_DENSE_RETRIEVER_CONFIG48DEFAULT_SPARSE_RETRIEVER_CONFIG48DEFAULT_GRAPH_RETRIEVER_CONFIG48DEFAULT_RETRIEVAL_FUSION_CONFIG48QueryDecomposer58createQueryDecomposer58RetrievalStrategySelector60createRetrievalStrategySelector60SourceQualityAssessor65createSourceQualityAssessor65IterativeRefinement67 +30 moreIntelligent document chunking for RAG systems
Document chunking for RAG: semantic/hierarchical/code chunkers, table/figure
extractors, and a ChunkingPipeline, with Zod-validated config.
createChunkId57createDocumentId57ChunkingError57DEFAULT_CHUNKING_CONFIG60DEFAULT_SEMANTIC_CONFIG60DEFAULT_HIERARCHICAL_CONFIG60DEFAULT_CODE_CONFIG60DEFAULT_TABLE_CONFIG60DEFAULT_FIGURE_CONFIG60DEFAULT_PIPELINE_CONFIG60DocumentSchema71ChunkMetadataSchema71ChunkingConfigSchema71DefaultSemanticChunker75 +16 moreKnowledge curation with duplicate detection, quality scoring, and merge workflows
Knowledge curation pipeline: DuplicateDetector, QualityScorer,
KnowledgeMerger, composed as KnowledgeCurator.
DEFAULT_DUPLICATE_DETECTOR_CONFIG26DEFAULT_QUALITY_SCORER_CONFIG26DEFAULT_KNOWLEDGE_MERGER_CONFIG26DEFAULT_KNOWLEDGE_CURATOR_CONFIG26DuplicateDetector33createDuplicateDetector33QualityScorer35createQualityScorer35KnowledgeMerger37createKnowledgeMerger37KnowledgeCurator39createKnowledgeCurator39createItemId43Embedding-service abstraction with OpenAI/Cohere/local providers, an
EmbeddingCache, batch processing, and similarity calculations.
CacheKey14ContentHash14createCacheKey14createContentHash14OpenAIEmbeddingModel14CohereEmbeddingModel14LocalEmbeddingModel14EmbeddingModel14CohereInputType14MODEL_MAX_TOKENS14MODEL_COSTS14EmbeddingResponse14BatchEmbeddingRequest14BatchEmbeddingResponse14 +37 moreEnterprise knowledge integration connectors for Iris
Enterprise knowledge connectors: Confluence/Notion/SharePoint/Google-Drive
connectors over a BaseConnector with a ConnectorFactory and OAuth2/API-token
auth.
createConnectorId90createSyncJobId90createRemoteDocumentId90createWebhookSubscriptionId90PROVIDER_CAPABILITIES98DEFAULT_RETRY_POLICY98DEFAULT_RATE_LIMIT_CONFIG98OAuth2TokenSchema105BasicAuthCredentialsSchema105ApiKeyCredentialsSchema105CredentialsSchema105BaseConnectorConfigSchema105SyncOptionsSchema105AuthProvider115 +15 moreKnowledge base export utilities for JSON-LD, RDF, and wiki formats
Knowledge export: JSON-LD, RDF, and Wiki exporters composed as
KnowledgeExporter (linked- data / semantic-web formats).
DEFAULT_KNOWLEDGE_EXPORTER_CONFIG29JSONLDExport31createJSONLDExport31RDFExport33createRDFExport33WikiExport35createWikiExport35KnowledgeExporter37createKnowledgeExporter37Automated fact checking pipeline with claim extraction, evidence retrieval, and veracity scoring
Automated fact-checking: ClaimExtractor, EvidenceRetriever,
SourceCredibilityScorer, VeracityScorer, composed as FactChecker.
DEFAULT_CLAIM_EXTRACTOR_CONFIG34DEFAULT_EVIDENCE_RETRIEVER_CONFIG34DEFAULT_SOURCE_CREDIBILITY_SCORER_CONFIG34DEFAULT_VERACITY_SCORER_CONFIG34DEFAULT_FACT_CHECKER_CONFIG34ClaimExtractor42createClaimExtractor42EvidenceRetriever44createEvidenceRetriever44SourceCredibilityScorer46createSourceCredibilityScorer46VeracityScorer51createVeracityScorer51FactChecker53 +3 moreKnowledge freshness tracking, temporal relevance scoring, and change notification system
Freshness tracking: FreshnessTracker, TemporalRelevanceScorer,
VersionTracker, ChangeNotifier, continuous index updater, composed as a
UnifiedFreshnessSystem.
VersionId54FreshnessRecordId54ChangeEventId54SubscriberId54IndexId54ContentHash54createVersionId54createFreshnessRecordId54createChangeEventId54createSubscriberId54createIndexId54createContentHash54DocumentType54FreshnessStatus54 +83 moreKnowledge graph storage, extraction, querying, and visualization for entities and relationships
Knowledge-graph stack: EntityExtractor, RelationshipExtractor,
KnowledgeGraphStore, GraphQueryEngine, GraphVisualization, and an
ingestTextIntoKnowledgeGraph pipeline.
DEFAULT_KNOWLEDGE_GRAPH_STORE_CONFIG39DEFAULT_ENTITY_EXTRACTOR_CONFIG39DEFAULT_RELATIONSHIP_EXTRACTOR_CONFIG39DEFAULT_GRAPH_QUERY_ENGINE_CONFIG39DEFAULT_GRAPH_VISUALIZATION_CONFIG39KnowledgeGraphStore47createKnowledgeGraphStore47EntityExtractor49createEntityExtractor49RelationshipExtractor51createRelationshipExtractor51GraphQueryEngine53createGraphQueryEngine53GraphVisualization55 +2 moreGraphRAG knowledge graph retrieval and multi-hop reasoning pipeline for Iris
GraphRAG: KnowledgeGraphBuilder, community detection, GraphSummarizer
(hierarchical), a GraphRAGQueryEngine (multi-hop), composed as
GraphRAGPipeline.
DEFAULT_GRAPH_COMMUNITY_DETECTION_CONFIG28DEFAULT_GRAPH_SUMMARIZER_CONFIG28DEFAULT_GRAPHRAG_PIPELINE_CONFIG28KnowledgeGraphBuilder34createKnowledgeGraphBuilder34GraphCommunityDetection36createGraphCommunityDetection36GraphSummarizer41createGraphSummarizer41GraphRAGQueryEngine43createGraphRAGQueryEngine43GraphRAGPipeline45createGraphRAGPipeline45Grounding and attribution system for AI-generated content with claim extraction, source citation, confidence scoring, fact verification, contradiction detection, and hallucination detection
Grounding/attribution for AI output: claim extraction, source citation,
confidence scoring, fact verification, contradiction + hallucination detection,
composed as DefaultGroundingPipeline.
SourceId15CitationId15VerificationId15ContradictionId15HallucinationId15SourceType15ReliabilityLevel15SourceMetadata15ClaimType15CitationConfig15ConfidenceFactors15ConfidenceLevel15ConfidenceConfig15VerificationCheck15 +68 moreIris Personal Document Indexing - File watching, format handling, metadata extraction, and PII detection for personal documents
Personal document indexing: DocumentIndexer with file watcher, format handler,
metadata extractor, change tracker, and a privacy filter, integrating with
@iris/knowledge.
createDocumentId106createWatchId106createIndexJobId106DEFAULT_PRIVACY_CONFIG112DEFAULT_WATCHER_CONFIG112DEFAULT_INDEXER_CONFIG112PrivacyFilterConfigSchema122FileWatcherConfigSchema122DocumentIndexerConfigSchema122FormatHandler132BinaryFormatHandler132CompositeFormatHandler132FORMAT_TO_CATEGORY132FORMAT_TO_CONTENT_FORMAT132 +37 moreComprehensive query expansion and reformulation system for RAG retrieval
Query expansion/reformulation for RAG: QueryExpander
(synonym/semantic/entity/PRF/LLM), QueryReformulator, HyDE
HypotheticalDocument, and a MultiQueryRetriever with fusion.
createQueryId55QueryIntent55QueryComplexity55QueryDomain55QueryEntity55EntityType55QueryExpansion55ExpandedQuery55ExpansionStats55QueryExpanderConfig55SynonymExpansionConfig55SemanticExpansionConfig55PRFExpansionConfig55LLMExpansionConfig55 +35 moreAdaptive chunking for RAG using content-aware sizing and quality scoring
Adaptive chunking: ContentTypeDetector, OptimalChunkSizer,
ChunkQualityScorer, composed as AdaptiveChunker.
DEFAULT_CONTENT_TYPE_DETECTOR_CONFIG25DEFAULT_OPTIMAL_CHUNK_SIZER_CONFIG25DEFAULT_CHUNK_QUALITY_SCORER_CONFIG25DEFAULT_ADAPTIVE_CHUNKER_CONFIG25ContentTypeDetector32createContentTypeDetector32OptimalChunkSizer34createOptimalChunkSizer34ChunkQualityScorer36createChunkQualityScorer36AdaptiveChunker38createAdaptiveChunker38RAG debugging toolkit with retrieval explanations, chunk inspection, and relevance visualizations
RAG observability: RetrievalExplainer, ChunkInspector,
RelevanceVisualizer, composed as RAGDebugger.
DEFAULT_RETRIEVAL_EXPLAINER_CONFIG24DEFAULT_CHUNK_INSPECTOR_CONFIG24DEFAULT_RELEVANCE_VISUALIZER_CONFIG24DEFAULT_RAG_DEBUGGER_CONFIG24RetrievalExplainer31createRetrievalExplainer31ChunkInspector33createChunkInspector33RelevanceVisualizer35createRelevanceVisualizer35RAGDebugger37createRAGDebugger37RAG evaluation stack with retrieval, generation, and end-to-end quality metrics
RAG evaluation: retrieval/generation/e2e metrics and an EvaluationDashboard,
composed as RAGEvaluator.
DEFAULT_RAG_EVALUATOR_CONFIG24RetrievalMetrics26createRetrievalMetrics26GenerationMetrics28createGenerationMetrics28E2ERAGMetrics30DEFAULT_E2E_RAG_METRICS_CONFIG30createE2ERAGMetrics30RAGEvaluator36createRAGEvaluator36EvaluationDashboard40createEvaluationDashboard40Multi-modal RAG retrieval for image, table, and code knowledge sources
Multi-modal retrieval: ImageRAG, TableRAG, CodeRAG, and a fusion-based
ranker (MultiModalFusion).
DEFAULT_IMAGE_RAG_CONFIG33DEFAULT_TABLE_RAG_CONFIG33DEFAULT_CODE_RAG_CONFIG33DEFAULT_MULTIMODAL_FUSION_CONFIG33ImageRAG40createImageRAG40TableRAG42createTableRAG42CodeRAG44createCodeRAG44MultiModalFusion46createMultiModalFusion46Real-time knowledge integration system with web search, news, academic papers, and social media monitoring
Real-time knowledge: web/news/academic search and social-media monitoring with a
multi-engine aggregator, composed as a UnifiedKnowledgeSystem.
SearchResultId63NewsArticleId63AcademicPaperId63SocialPostId63createSearchResultId63createNewsArticleId63createAcademicPaperId63createSocialPostId63NewsProvider63AcademicProvider63SocialPlatform63WebSearchOptions63WebSearchResponse63KnowledgePanel63 +54 moreHybrid retrieval system combining dense and sparse retrieval with advanced reranking
Hybrid retrieval: dense (bi-encoder) + sparse retrievers, multiple fusion methods, ColBERT-style multi-vector retrieval, cross-encoder reranking, and evaluation metrics.
IndexId48createDocumentId48createIndexId48IndexedDocument48RetrievalResults48RetrieverType48EmbeddingService48MultiVectorEmbeddingService48SparseVector48Tokenizer48HNSWConfig48IVFConfig48PQConfig48IndexConfig48 +72 moreKnowledge versioning with change tracking, comparisons, and rollback workflows
Knowledge versioning: ChangeTracker, VersionComparison,
RollbackCapability, composed as KnowledgeVersioner.
DEFAULT_CHANGE_TRACKER_CONFIG35DEFAULT_VERSION_COMPARISON_CONFIG35DEFAULT_ROLLBACK_CAPABILITY_CONFIG35DEFAULT_KNOWLEDGE_VERSIONER_CONFIG35ChangeTracker42createChangeTracker42VersionComparison44createVersionComparison44RollbackCapability46createRollbackCapability46KnowledgeVersioner48createKnowledgeVersioner48createKnowledgeEntityId56createKnowledgeVersionId56 +1 morememory-* (13)#
Memory analytics library for usage stats, retrieval patterns, growth trends, and quality metrics
Memory analytics: usage stats, growth trends, quality metrics, retrieval-pattern analysis, and an analytics dashboard.
createReportId90createSnapshotId90createTrendId90DEFAULT_MEMORY_USAGE_CONFIG93DEFAULT_RETRIEVAL_PATTERN_CONFIG93DEFAULT_GROWTH_TREND_CONFIG93DEFAULT_QUALITY_METRICS_CONFIG93DEFAULT_ANALYTICS_EXPORT_OPTIONS93DEFAULT_MEMORY_ANALYTICS_DASHBOARD_CONFIG93MemoryUsageStatsCollector103createMemoryUsageStatsCollector103MemoryDataProvider103RetrievalPatternsAnalyzer110createRetrievalPatternsAnalyzer110 +20 moreMemory consolidation system for Iris - natural forgetting, importance scoring, and memory compression
Memory consolidation: forgetting-curve DecayAlgorithm, ImportanceScorer,
SummaryGenerator, MemoryClusterer, composed as ConsolidationEngine.
DEFAULT_TIER_DECAY_CONFIG57DEFAULT_IMPORTANCE_CONFIG57DEFAULT_SUMMARY_CONFIG57DEFAULT_CLUSTERING_CONFIG57DEFAULT_ENGINE_CONFIG57DecayAlgorithm69createDecayAlgorithm69calculateOptimalDecayRate69calculateHalfLife69getDefaultStepThresholds69simulateDecay69ImportanceScorer82createImportanceScorer82getContentTypeScore82 +13 moreMemory debugging tools for the Iris memory subsystem
Memory debugging: MemoryDebugger, retrieval explainer, timeline + change
tracking, and a debug-session manager.
createDebugSessionId93createEventId93createSnapshotId93DEFAULT_RANKING_WEIGHTS93MemoryDebugger101createMemoryDebugger101DebuggerStorage101EventStorage101ValidationRule101RetrievalExplainer110createRetrievalExplainer110RetrievalExplainerConfig110TimelineTracker117createTimelineTracker117 +10 moreIris episodic memory - event-based autobiographical memory with temporal context
Episodic memory: event-based autobiographical episodes with temporal context, a
MemorableInteractionDetector, MilestoneTracker, task-completion records, and
episodic retrieval.
generateInteractionId73createTaskRecordId73generateTaskRecordId73createFeedbackId73generateFeedbackId73createMilestoneId73generateMilestoneId73DEFAULT_TASK_COMPLETION_CONFIG73DEFAULT_FEEDBACK_HISTORY_CONFIG73DEFAULT_MILESTONE_TRACKER_CONFIG73DEFAULT_EPISODIC_RETRIEVAL_CONFIG73MemorableInteractionDetector95createMemorableInteractionDetector95TaskCompletionRecords104 +17 moreLong-term memory (LTM) implementation for Iris AI agents with persistent storage and semantic retrieval
Long-term memory: persistent LongTermMemory, PreferenceStore,
PatternStore, CorrectionStore, plus LTM consolidation/retrieval.
PatternId13CorrectionId13ConsolidationJobId13generatePatternId13generateCorrectionId13generateConsolidationJobId13PreferenceConfidence13PreferenceEntry13PatternStatus13PatternEntry13CorrectionStatus13CorrectionEntry13LTMQueryOptions13VectorSearchOptions13 +42 moreMemory migration library for importing from ChatGPT, Claude, and custom AI systems
Memory import from external AI systems: ChatGPT/Claude/custom importers over a
BaseMemoryImporter (with content hashing) and a migration pipeline.
ImportSource14RawImportedMessage14RawAttachment14ChatGPTConversation14ChatGPTMessageNode14ChatGPTMessage14ChatGPTMessageMetadata14ChatGPTUserData14ClaudeConversation14ClaudeChatMessage14ClaudeAttachment14ClaudeFile14ClaudeProject14ClaudeAccountData14 +47 moreHigh-performance memory retrieval system with hybrid search, BM25, semantic matching, and multi-source fusion
High-performance memory retrieval (<100ms target): hybrid semantic + BM25
keyword search, temporal search, multi-factor relevance ranking, and
multi-source fusion, composed as MemoryRetriever (with an embedding-service
seam).
DEFAULT_SEMANTIC_CONFIG110DEFAULT_KEYWORD_CONFIG110DEFAULT_TEMPORAL_CONFIG110DEFAULT_RANKING_WEIGHTS110DEFAULT_RANKING_CONFIG110DEFAULT_FUSION_CONFIG110DEFAULT_RETRIEVER_CONFIG110EMPTY_METRICS110SemanticSearch125createSemanticSearch125batchCalculateSimilarities125findTopK125calculateCentroid125calculateEmbeddingVariance125 +23 moreMemory sharing library for access control, shared spaces, and collaborative synchronization
Memory sharing/collaboration: MemoryAccessManager, shared spaces, and
synchronization services.
SpaceId14PolicyId14SyncId14createShareId14createSpaceId14createPolicyId14createSyncId14Principal14MemoryVisibility14MemoryAction14MemoryPermission14PermissionConditions14TimeWindow14MEMORY_ROLE_PERMISSIONS14 +71 moreShort-term memory (STM) implementation for Iris AI agents
Short-term/working memory: ShortTermMemory, WorkingMemory, recent-references
tracking, STM eviction, and temporal decay.
ReferenceId11TaskContextId11createSlotId11generateSlotId11createReferenceId11generateReferenceId11createTaskContextId11generateTaskContextId11WorkingMemoryConfig11RecentReferencesConfig11TemporalDecayConfig11STMEvictionConfig11DEFAULT_STM_CONFIG11DEFAULT_WORKING_MEMORY_CONFIG11 +33 moreLLM-callable memory management tools for Iris AI assistants
LLM-callable memory tools: tool definitions, handlers, and an executor for
letting an assistant manage its own memory (with formatToolsForClaude).
DEFAULT_MEMORY_TOOLS_CONFIG106generateToolCallId112validateRequired112runcateContent112formatMemoryForOutput112oMemorySearchOptions112oCreateMemoryOptions112oMemoryEditOptions112oUpdateMemoryOptions112memoryReadToolDefinition127memoryWriteToolDefinition127memoryEditToolDefinition127memoryDeleteToolDefinition127memorySummaryToolDefinition127 +29 moreMemory tier transition system for Iris AI agents with promotion, demotion, and consolidation
Memory-tier transitions: MemoryPromoter (STM→LTM), MemoryDemoter
(LTM→archival), ImportanceScorer, a consolidation scheduler, and transition
metrics.
BatchId50createTransitionId50createBatchId50generateTransitionId50generateBatchId50ImportanceWeights50ImportanceScore50ImportanceScorerConfig50ImportanceScoringContext50ImportanceFeedback50CONTENT_TYPE_IMPORTANCE50DEFAULT_IMPORTANCE_SCORER_CONFIG50TransitionCandidate50MemoryPromoterConfig50 +45 moreMemory visualization: graph, timeline, topic-cluster, and relationship view builders behind a visualization interface.
createGraphNodeId68createGraphEdgeId68createClusterId68createViewId68DEFAULT_ANIMATION_CONFIG71DEFAULT_GRAPH_CONFIG71DEFAULT_TIMELINE_CONFIG71DEFAULT_TOPIC_CLUSTER_CONFIG71DEFAULT_RELATIONSHIP_VIEW_CONFIG71DEFAULT_EXPORT_OPTIONS71MemoryGraphBuilder81TimelineViewBuilder84TopicClusterViewBuilder87RelationshipViewBuilder90 +7 moreMemory writing system for Iris AI agents with validation, merging, and conflict resolution
Memory writing: MemoryWriter, MemoryValidator, MemoryMerger (dedup),
MemoryUpdater, and a conflict resolver with batch-write support.
DEFAULT_VALIDATOR_CONFIG93DEFAULT_MERGE_CONFIG93DEFAULT_CONFLICT_CONFIG93DEFAULT_WRITER_CONFIG93EMPTY_WRITER_STATS93MemoryWriter102createMemoryWriter102WriteOptionsBuilder102writeMemory102MemoryValidator110createMemoryValidator110createValidationRule110MemoryMerger117createMemoryMerger117 +10 morepersonalization-* (3)#
LCMP-style personalization benchmarking with metrics, stress testing, and regression detection
Personalization benchmarking (libs/iris/personalization/benchmarking):
PersonalizationMetrics, ContextLengthStressTest,
PersonalizationRegression, and an LCMPBenchmarkRunner.
PersonalizationMetrics5ContextLengthStressTest6PersonalizationRegression7LCMPBenchmarkRunner8DEFAULT_PERSONALIZATION_METRIC_WEIGHTS10DEFAULT_CONTEXT_LENGTH_STRESS_CONFIG10DEFAULT_PERSONALIZATION_REGRESSION_THRESHOLDS10DEFAULT_LCMP_BENCHMARK_RUNNER_CONFIG10State-aware personalization engine with concept tracking, variation detection, context windows, and continual learning
State-aware personalization: PersonalizedConceptTracker, VariationPerceiver,
a personalization context window, StateAwareResponseGenerator, and a
ContinualPersonalizationLearner, composed as
StateAwarePersonalizationEngine.
PersonalizedConceptTracker5VariationPerceiver6PersonalizationContextWindow7StateAwareResponseGenerator8ContinualPersonalizationLearner9StateAwarePersonalizationEngine10DEFAULT_STATE_AWARE_PERSONALIZATION_CONFIG12DEFAULT_CONCEPT_VARIATION_CONFIG12Persistent and portable user model persistence for state-aware personalization
User-model persistence: snapshot, versioning, migration, export, and
privacy-controls modules over a user-model-persistence-service.
UserModelSnapshot5UserModelVersioning6UserModelMigration7UserModelExport8UserModelPrivacyControls9InMemoryUserModelPersistenceStore10UserModelPersistenceService10DEFAULT_USER_MODEL_VERSIONING_CONFIG15DEFAULT_USER_MODEL_PRIVACY_POLICY15DEFAULT_USER_MODEL_PERSISTENCE_CONFIG15oUserModelId47oUserModelVersionId47oContextEntryId47oSessionId47platform-* (11)#
Enterprise admin console backend for Iris platform
Enterprise admin-console backend: EnterpriseAdminService with a default
config. Small but real (3 modules).
Usage-based billing primitives for Iris platform APIs
Usage billing: UsageTracker, BillingCalculator, InvoiceGenerator, payment
integration.
DEFAULT_USAGE_TRACKER_CONFIG32DEFAULT_BILLING_CALCULATOR_CONFIG32DEFAULT_INVOICE_GENERATOR_CONFIG32DEFAULT_PAYMENT_INTEGRATION_CONFIG32DEFAULT_BILLING_PLANS32UsageTracker40createUsageTracker40BillingCalculator42createBillingCalculator42InvoiceGenerator44createInvoiceGenerator44PaymentIntegration46MockPaymentAdapter46createPaymentIntegration46OpenAPI-based SDK code generator for Iris platform clients
SDK code generation: OpenAPIToSDK, TypeGenerator, ClientGenerator,
composed as SDKCodeGenerator.
DEFAULT_OPENAPI_TO_SDK_CONFIG34DEFAULT_TYPE_GENERATOR_CONFIG34DEFAULT_CLIENT_GENERATOR_CONFIG34DEFAULT_SDK_CODE_GENERATOR_CONFIG34OpenAPIToSDK41createOpenAPIToSDK41TypeGenerator43createTypeGenerator43ClientGenerator45createClientGenerator45SDKCodeGenerator48createSDKCodeGenerator48Composable API gateway runtime for Iris platform endpoints
API gateway: RequestRouter, MiddlewarePipeline, ResponseTransformer, and
APIGateway with a FetchUpstreamTransport.
DEFAULT_REQUEST_ROUTER_CONFIG26DEFAULT_MIDDLEWARE_PIPELINE_CONFIG26DEFAULT_RESPONSE_TRANSFORM_RULE26DEFAULT_RESPONSE_TRANSFORMER_CONFIG26DEFAULT_API_GATEWAY_CONFIG26RequestRouter34createRequestRouter34MiddlewarePipeline36createMiddlewarePipeline36ResponseTransformer38createResponseTransformer38APIGateway40FetchUpstreamTransport40createAPIGateway40Endpoint-aware tiered rate limiting for Iris platform APIs
Rate limiting: RateLimiter, TieredRateLimits, BurstHandling, and
RateLimitHeaders.
DEFAULT_BURST_POLICY28DEFAULT_FREE_POLICY28DEFAULT_PRO_POLICY28DEFAULT_ENTERPRISE_POLICY28DEFAULT_INTERNAL_POLICY28DEFAULT_TIERED_PLANS28DEFAULT_TIERED_RATE_LIMITS_CONFIG28DEFAULT_BURST_HANDLING_CONFIG28DEFAULT_RATE_LIMIT_HEADERS_CONFIG28DEFAULT_RATE_LIMITER_CONFIG28TieredRateLimits41createTieredRateLimits41BurstHandling43createBurstHandling43 +4 moreEnterprise reporting service for Iris platform
Enterprise reporting: EnterpriseReportingService with default metrics-by-type
config. Small but real (3 modules).
EnterpriseReportingService7createEnterpriseReportingService7DEFAULT_METRICS_BY_TYPE12DEFAULT_REPORTING_CONFIG12SDK documentation generation toolkit for Iris platform SDKs
SDK documentation generation: CodeSampleGenerator, QuickstartGenerator,
TutorialGenerator, composed as SDKDocGenerator.
DEFAULT_CODE_SAMPLE_GENERATOR_CONFIG33DEFAULT_QUICKSTART_GENERATION_CONFIG33DEFAULT_TUTORIAL_GENERATION_CONFIG33DEFAULT_SDK_DOC_GENERATOR_CONFIG33CodeSampleGenerator40createCodeSampleGenerator40QuickstartGenerator42createQuickstartGenerator42TutorialGenerator44createTutorialGenerator44SDKDocGenerator46createSDKDocGenerator46SDK integration, compatibility, and performance testing suite for Iris platform
SDK test tooling: IntegrationTests, CompatibilityTests, PerformanceTests,
composed as SDKTestSuite.
DEFAULT_INTEGRATION_TESTS_CONFIG40DEFAULT_COMPATIBILITY_TESTS_CONFIG40DEFAULT_PERFORMANCE_TESTS_CONFIG40DEFAULT_SDK_TEST_SUITE_CONFIG40IntegrationTests47createIntegrationTests47CompatibilityTests49createCompatibilityTests49PerformanceTests51createPerformanceTests51SDKTestSuite54createSDKTestSuite54SDK version lifecycle, semantic versioning, and migration guidance
SDK version management: SemVerManager, DeprecationManager, breaking-change
detector, and a migration-guide generator, composed as SDKVersionManager.
DEFAULT_SEMVER_MANAGER_CONFIG30DEFAULT_DEPRECATION_MANAGER_CONFIG30DEFAULT_MIGRATION_GUIDE_GENERATOR_CONFIG30DEFAULT_BREAKING_CHANGE_DETECTOR_CONFIG30DEFAULT_SDK_VERSION_MANAGER_CONFIG30SemVerManager38createSemVerManager38DeprecationManager40createDeprecationManager40MigrationGuideGenerator42createMigrationGuideGenerator42BreakingChangeDetector47createBreakingChangeDetector47SDKVersionManager52 +1 moreEnterprise SLA management for Iris platform services
Enterprise SLA management — a smaller sibling of platform-sla-management
(barrel re-exporting sla-manager/types, 3 modules). Honest overlap: both
expose an SLA manager; this one is the leaner variant.
Webhook orchestration toolkit for Iris platform events
Webhook delivery: WebhookManager, EventDispatcher, RetryHandler,
WebhookSecurity (signing/verification).
DEFAULT_WEBHOOK_RETRY_POLICY27DEFAULT_WEBHOOK_SECURITY_CONFIG27DEFAULT_RETRY_HANDLER_CONFIG27DEFAULT_EVENT_DISPATCHER_CONFIG27DEFAULT_WEBHOOK_MANAGER_CONFIG27WebhookManager35createWebhookManager35RetryHandler37createRetryHandler37WebhookSecurity39createWebhookSecurity39EventDispatcher41FetchEventDeliveryTransport41createEventDispatcher41privacy-* (19)#
Strong data anonymization toolkit with k-anonymity and l-diversity validation
Data anonymization: KAnonymity, LDiversity, a DataAnonymizer, and an
anonymization validator, with real quasiKey/pseudonymize/generalizeValue
utilities.
DEFAULT_ANONYMIZATION_CONFIG23clamp25quasiKey25hashText25seudonymize25generalizeValue25KAnonymity27createKAnonymity27LDiversity29createLDiversity29AnonymizationValidator31createAnonymizationValidator31AnonymizationValidatorDependencies31DataAnonymizer37 +2 morePrivacy audit toolkit with compliance checks, reports, and remediation planning
Privacy audit: ComplianceChecker, AuditReportGenerator,
RemediationSuggester, composed as PrivacyAuditor, with risk-scoring
utilities.
DEFAULT_COMPLIANCE_CHECKER_CONFIG29DEFAULT_PRIVACY_AUDITOR_CONFIG29DEFAULT_AUDIT_REPORT_GENERATOR_CONFIG29DEFAULT_REMEDIATION_SUGGESTER_CONFIG29stableId36clamp36controlCoverage36riskScoreFromFindings36daysSince36ComplianceChecker38createComplianceChecker38PrivacyAuditor40createPrivacyAuditor40PrivacyAuditorDependencies40 +4 morePrivacy-focused secure communication library - TLS enforcement, certificate pinning, secure WebSocket, and API gateway
Secure communication: TLSEnforcement, CertificatePinning, SecureWebSocket,
and a SecureGateway.
TLSEnforcer69createTLSEnforcer69createStrictTLSEnforcer69isSecureCipher69isSecureTLSVersion69getRecommendedCiphers69SECURE_CIPHER_SUITES69WEAK_CIPHERS69DEFAULT_TLS_CONFIG69POLICY_CONFIGS69CertificatePinManager83createCertificatePinManager83createCertificatePin83calculatePublicKeyPin83 +24 morePrivacy dashboard primitives for inventory, consent, and deletion governance
Privacy dashboard: DataInventoryView, ConsentManagerUI,
DeletionRequestsUI, composed as a PrivacyDashboardUI.
DEFAULT_DATA_INVENTORY_VIEW_CONFIG28DEFAULT_CONSENT_MANAGER_UI_CONFIG28DEFAULT_DELETION_REQUESTS_UI_CONFIG28DEFAULT_PRIVACY_DASHBOARD_UI_CONFIG28stableId35daysFromNow35average35initCategoryCounts35retentionRisk35DataInventoryView37createDataInventoryView37ConsentManagerUI39createConsentManagerUI39DeletionRequestsUI41 +4 moreEnd-to-end encryption library for Iris privacy module with encrypted storage, model I/O, zero-knowledge proofs, and secure multi-party computation
E2E encryption (~14 modules): crypto primitives (AES-256-GCM, ChaCha20-Poly1305,
Ed25519), KeyManager (rotation/audit), Double-Ratchet E2E, encrypted
storage/model-IO, secure MPC, and zero-knowledge proofs.
randomUUID26randomInt26generateIV26generateSalt26generateRSAKeyPair26generateECDHKeyPair26generateEd25519KeyPair26deriveKeyHKDF26deriveKeyScrypt26deriveKey26decryptSymmetric26decryptRSA26computeECDHSharedSecret26verifyEd2551926 +55 moreIris privacy-preserving local inference - on-device AI processing with Ollama and llama.cpp support
On-device AI inference (~23 modules): Ollama and llama.cpp runtimes, a
ModelManager/ ModelOptimizer, GPU/NPU accelerator detection, offline
cache/sync/features, and hybrid cloud/edge routing, composed as a
LocalInferenceEngine.
InferenceOptionsSchema64ChatMessageSchema64InferenceRequestSchema64EmbeddingRequestSchema64LocalInferenceEngine75createLocalInferenceEngine75LocalInferenceEngineOptions75InferenceRuntime75OllamaRuntime86createOllamaRuntime86OllamaRuntimeOptions86LlamaCppRuntime86createLlamaCppRuntime86LlamaCppRuntimeOptions86 +90 moreData minimization toolkit with detection, retention enforcement, and automated purging
Data minimization: UnnecessaryDataDetector, DataMinimizer,
RetentionEnforcer, AutoPurger, with end-to-end minimization reports.
DEFAULT_UNNECESSARY_DATA_DETECTOR_CONFIG27DEFAULT_RETENTION_ENFORCER_CONFIG27DEFAULT_AUTO_PURGER_CONFIG27DEFAULT_DATA_MINIMIZER_CONFIG27ageInDays34isSensitiveField34shouldKeepField34sanitizeFields34complianceScore34UnnecessaryDataDetector42createUnnecessaryDataDetector42RetentionEnforcer47createRetentionEnforcer47AutoPurger49 +4 morePrivate cloud compute layer with secure enclave processing, ephemeral execution, and no-retention guarantees
Private-cloud compute: SecureEnclaveProcessor, EphemeralProcessing,
AuditableCompute, HardenedServerConfig (with a hardened baseline),
NoDataRetention, composed as a PrivateCloudComputeLayer.
SecureEnclaveProcessor5EphemeralProcessing6AuditableCompute7HardenedServerConfig8HARDENED_BASELINE_CONFIG8NoDataRetention9PrivateCloudComputeLayer10DEFAULT_PRIVATE_CLOUD_CONFIG12AI content safety library - content filtering, harmful content detection, jailbreak resistance, age-appropriate responses, toxicity detection
Content safety: multi-layer ContentFilter, HarmfulContentDetector, jailbreak
resistance, age-appropriate responses, ToxicityDetector, composed as
SafetyChecker.
SeverityLevelSchema74ContentActionSchema74SafetyCategorySchema74ToxicityTypeSchema74SEVERITY_ORDER82compareSeverity82maxSeverity82meetsSeverityThreshold82ContentFilter88createContentFilter88createKeywordLayer88createRegexLayer88createHeuristicLayer88KeywordFilterLayer88 +25 moreAI transparency features for identity disclosure, capability limitations, decision explanation, and uncertainty disclosure
AI transparency: identity disclosure, capability-limitation disclosure,
DecisionExplainer, uncertainty disclosure, composed as TransparencySystem.
AIIdentityDisclosure91createAIIdentityDisclosure91DEFAULT_AI_IDENTITY91DEFAULT_DISCLOSURE_TEMPLATES91DEFAULT_AI_IDENTITY_DISCLOSURE_CONFIG91CapabilityLimitations99createCapabilityLimitations99DEFAULT_CAPABILITIES99DEFAULT_LIMITATIONS99DEFAULT_CAPABILITY_LIMITATIONS_CONFIG99DecisionExplainer107createDecisionExplainer107DEFAULT_DECISION_EXPLAINER_CONFIG107UncertaintyDisclosureManager114 +8 moreCompliance certification management for SOC2, HIPAA, GDPR, and ISO27001
Compliance certification for SOC2/HIPAA/GDPR/ISO27001
(ComplianceCertificationManager/createComplianceCertificationManager). Small
(3 modules) but real.
ComplianceCertificationManager7createComplianceCertificationManager7ALL_CONTROLS12DEFAULT_COMPLIANCE_CONFIG12GDPR_CONTROLS12HIPAA_CONTROLS12ISO27001_CONTROLS12SOC2_CONTROLS12Data Loss Prevention service for scanning and protecting sensitive data
Data-loss prevention: a single data-loss-prevention module re-exported by the
barrel. Thin (the smallest privacy-security lib) but real, not a scaffold.
Prompt injection and jailbreak defense with sanitization and adaptive response strategy
Prompt-injection defense: PromptInjectionDetector, JailbreakDetector,
InputSanitizer, composed as DefenseStrategy.
DEFAULT_PROMPT_INJECTION_RULES33DEFAULT_JAILBREAK_RULES33DEFAULT_PROMPT_INJECTION_DETECTOR_CONFIG33DEFAULT_JAILBREAK_DETECTOR_CONFIG33DEFAULT_INPUT_SANITIZER_CONFIG33DEFAULT_DEFENSE_POLICY33DEFAULT_DEFENSE_STRATEGY_CONFIG33PromptInjectionDetector43createPromptInjectionDetector43JailbreakDetector48createJailbreakDetector48InputSanitizer50createInputSanitizer50DefenseStrategy53 +1 moreComprehensive security event, access, change, and alert logging
Security logging: SecurityLogger, AccessLogger, ChangeLogger,
SecurityAlertLogger with default configs.
DEFAULT_SECURITY_LOGGER_CONFIG29DEFAULT_SECURITY_ALERT_LOGGER_CONFIG29SecurityLogger31createSecurityLogger31AccessLogger34createAccessLogger34ChangeLogger37createChangeLogger37SecurityAlertLogger39createSecurityAlertLogger39Automated penetration testing suite with vulnerability scanning, fuzzing, and reporting
Penetration testing: VulnerabilityScanner, FuzzTester, SecurityReporter,
composed as SecurityTestSuite.
DEFAULT_VULNERABILITY_RULES30DEFAULT_VULNERABILITY_SCANNER_CONFIG30DEFAULT_FUZZ_MUTATORS30DEFAULT_FUZZ_TESTER_CONFIG30DEFAULT_SECURITY_TEST_SUITE_CONFIG30DEFAULT_SECURITY_REPORTER_CONFIG30VulnerabilityScanner39createVulnerabilityScanner39FuzzTester41createFuzzTester41SecurityTestSuite44createSecurityTestSuite44SecurityReporter46createSecurityReporter46Threat detection stack with abuse signatures, anomaly detection, and adaptive response
Threat detection: AbusePatternsDetector, behavioral AnomalyDetector,
ThreatResponse, composed as ThreatDetector, with
haversineKm/severity-weight utilities.
DEFAULT_ABUSE_PATTERN_RULES27DEFAULT_ABUSE_PATTERNS_DETECTOR_CONFIG27DEFAULT_ANOMALY_DETECTOR_CONFIG27DEFAULT_THREAT_RESPONSE_CONFIG27DEFAULT_THREAT_DETECTOR_CONFIG27stableId35clamp35severityWeight35haversineKm35avg35AbusePatternsDetector37createAbusePatternsDetector37AnomalyDetector39createAnomalyDetector39 +5 moreData sovereignty and compliance controls for Iris AI
Data sovereignty: data-residency controls, GDPR (Arts. 15-22/30/33-34) and
CCPA/CPRA compliance modules, cross-border transfer, and right-to-deletion, with
an extensive typed surface (residency/minimization/consent/analytics) and a
DataSovereigntyManager.
DataResidencyService16createDataResidencyService16createInMemoryDataResidencyRepository16InMemoryDataResidencyRepository16DataResidencyRepository16DataResidencyServiceConfig16ResidencyCheckResult16ZoneSelectionResult16GDPRComplianceService28createGDPRComplianceService28createInMemoryGDPRRepository28InMemoryGDPRRepository28GDPRRepository28GDPRComplianceServiceConfig28 +64 moreThird-party model consent flow with data minimization, audit logging, and user preference management
Third-party-model consent: ThirdPartyModelRegistry, ConsentPromptUI,
DataMinimizationPreprocessor, ThirdPartyAuditLog, UserPreferenceStore,
composed as ThirdPartyConsentFlow.
ThirdPartyModelRegistry5ConsentPromptUI6DataMinimizationPreprocessor7ThirdPartyAuditLog8UserPreferenceStore9ThirdPartyConsentFlow10Tiered privacy-aware compute routing with explicit consent and fallback governance
Tiered compute routing by sensitivity: ComplexityEstimator,
PrivacySensitivityClassifier, UserConsentManager, TierRouter,
TierFallbackChain, composed as TieredComputeOrchestrator.
ComplexityEstimator5PrivacySensitivityClassifier6UserConsentManager7TierRouter8TierFallbackChain9TieredComputeOrchestrator10DEFAULT_TIERED_COMPUTE_CONFIG12sdk-* (4)#
Official TypeScript/JavaScript SDK for the Iris AI Assistant API
The official TypeScript/JavaScript SDK (libs/iris/sdk/typescript): an
IrisClient/Iris client with createClientFromEnv,
conversation/agent/memory/knowledge sub-clients, and an HTTP layer
(client.chat(...)).
IrisClient33Iris33createClient33createClientFromEnv33ConversationClient39createConversationClient39MemoryClient39createMemoryClient39AgentClient39createAgentClient39KnowledgeClient39createKnowledgeClient39HttpClient54createHttpClient54 +19 moreKotlin SDK (libs/iris/sdk/kotlin): a Gradle module with IrisClient and
Agent/Conversation/Knowledge/Memory clients, an HttpClient, typed Types.kt,
and a client test — the JVM/Android client view of the Iris API.
Rust SDK (libs/iris/sdk/rust): a iris_sdk crate (lib.rs) with an async
IrisClient, per-domain client modules (agent/conversation/knowledge/memory),
an HTTP layer, typed errors/types — type-safe async access to the API.
Swift SDK (libs/iris/sdk/swift): a SwiftPM package (IrisSDK) with
IrisClient, Agent/Conversation/Knowledge/Memory clients, an HTTPClient,
typed Types.swift, and tests — the Apple-platform client.
testing-* (4)#
Chaos engineering toolkit for Iris platform reliability testing
Chaos testing: NetworkChaos, ServiceChaos, DataChaos, composed in a
chaos-test framework.
ChaosTestFramework5createChaosTestFramework5ChaosTestFrameworkDependencies5NetworkChaos11createNetworkChaos11NetworkChaosFaultOptions11ServiceChaos16createServiceChaos16ServiceChaosFaultOptions16DataChaos21createDataChaos21DataChaosFaultOptions21clamp23createEmptyImpact23 +31 moreLoad testing toolkit for Iris reliability and performance validation
Load testing: ScenarioBuilder, LoadProfiler, LoadReporter, composed as a
load-test suite.
ScenarioBuilder5createScenarioBuilder5LoadProfiler6createLoadProfiler6LoadTestSuite7createLoadTestSuite7LoadTestSuiteDependencies7LoadReporter12createLoadReporter12DEFAULT_LOAD_PROFILER_CONFIG14DEFAULT_LOAD_REPORTER_CONFIG14DEFAULT_LOAD_TEST_SUITE_CONFIG14LoadExecutionRecord14LoadOperation14 +14 moreSynthetic monitoring toolkit for Iris reliability validation
Synthetic monitoring: SyntheticMonitor, health-check probes, user-journey
tests, and alert integration.
HealthCheckProbes5createHealthCheckProbes5HealthCheckProbesDependencies5UserJourneyTests10createUserJourneyTests10UserJourneyTestsDependencies10AlertIntegration15createAlertIntegration15AlertIntegrationDependencies15SyntheticMonitor20createSyntheticMonitor20SyntheticMonitorDependencies20DEFAULT_ALERT_INTEGRATION_CONFIG26DEFAULT_HEALTH_CHECK_PROBES_CONFIG26 +27 moreVisual regression testing toolkit for Iris
Visual regression testing: PixelDiffAnalyzer, screenshot comparison, a
visual-test framework, and a regression reporter.
PixelDiffAnalyzer5createPixelDiffAnalyzer5ScreenshotComparison6createScreenshotComparison6createScreenshotComparisonWithAnalyzer6ScreenshotComparisonDependencies6VisualTestFramework12createVisualTestFramework12VisualTestFrameworkDependencies12VisualRegressionReporter17createVisualRegressionReporter17DEFAULT_PIXEL_DIFF_ANALYZER_CONFIG22DEFAULT_SCREENSHOT_COMPARISON_CONFIG22DEFAULT_SCREENSHOT_THRESHOLDS22 +22 morevision-* (4)#
Diagram generation from natural language: FlowchartCreator, MindMapCreator,
architecture-diagram creator, composed as DiagramGenerator.
DEFAULT_DIAGRAM_GENERATOR_CONFIG29FlowchartCreator31createFlowchartCreator31MindMapCreator33createMindMapCreator33ArchitectureDiagramCreator35createArchitectureDiagramCreator35DiagramGenerator40createDiagramGenerator40Visual memory: ImageMemoryStore, VisualContextRecall,
ImageSimilaritySearch, VisualHistoryTimeline.
DEFAULT_IMAGE_MEMORY_STORE_CONFIG31DEFAULT_VISUAL_CONTEXT_RECALL_CONFIG31DEFAULT_IMAGE_SIMILARITY_SEARCH_CONFIG31DEFAULT_VISUAL_HISTORY_TIMELINE_CONFIG31ImageMemoryStore38createImageMemoryStore38VisualContextRecall40createVisualContextRecall40ImageSimilaritySearch42createImageSimilaritySearch42VisualHistoryTimeline44createVisualHistoryTimeline44Visual search: image indexing, ImageToTextQuery, SimilarImageSearch,
ObjectSearch, composed as VisualSearchEngine.
DEFAULT_VISUAL_SEARCH_ENGINE_CONFIG32DEFAULT_IMAGE_TO_TEXT_QUERY_CONFIG32DEFAULT_SIMILAR_IMAGE_SEARCH_CONFIG32DEFAULT_OBJECT_SEARCH_CONFIG32ImageToTextQuery39createImageToTextQuery39SimilarImageSearch41createSimilarImageSearch41ObjectSearch43createObjectSearch43VisualSearchEngine45createVisualSearchEngine45voice-* (10)#
Speech recognition system with real-time STT, streaming transcription, voice activity detection, and multi-language support
Speech-recognition system (libs/iris/multimodal/voice/recognition, ~30
modules): real-time STT (SpeechRecognizer), streaming transcription, VAD,
noise processing, accent/dialect handling, multilingual + code-switch detection,
speaker diarization/identification/ verification, anti-spoofing, composed as
VoiceRecognitionSystem.
createTranscriptId76createSpeakerId76createChunkId76DEFAULT_STREAMING_CONFIG76DEFAULT_VAD_CONFIG76VoiceActivityDetector92createVoiceActivityDetector92NoiseProcessor94createNoiseProcessor94AccentHandler96createAccentHandler96StreamingTranscription98createStreamingTranscription98SpeechRecognizer100 +316 moreVoice biometrics: VoiceBiometrics, VoiceEnrollment, VoiceVerification, and
fallback authentication.
DEFAULT_VOICE_BIOMETRICS_CONFIG26DEFAULT_FALLBACK_AUTHENTICATION_CONFIG26VoiceBiometrics31createVoiceBiometrics31VoiceEnrollment33createVoiceEnrollment33FallbackAuthentication35createFallbackAuthentication35VoiceVerification37createVoiceVerification37Voice command handling: VoiceCommandParser, CustomCommandTraining,
CommandConfirmation, CommandAliases.
DEFAULT_COMMAND_ALIASES_CONFIG32DEFAULT_CUSTOM_COMMAND_TRAINING_CONFIG32DEFAULT_COMMAND_CONFIRMATION_CONFIG32DEFAULT_VOICE_COMMAND_PARSER_CONFIG32CommandAliases39createCommandAliases39CustomCommandTraining41createCustomCommandTraining41CommandConfirmation43createCommandConfirmation43VoiceCommandParser45createVoiceCommandParser45Full-duplex voice conversation engine with natural turn-taking
Full-duplex voice conversation (~12 modules): a full-duplex-engine with
VAD/turn-taking/ interruption/backchannel handling, prosody and emotion
sub-modules, and WebRTC voice transport, with rich turn-completion helpers.
DEFAULT_VAD_CONFIG101DEFAULT_TURN_TAKING_CONFIG101DEFAULT_INTERRUPTION_CONFIG101DEFAULT_BACKCHANNEL_CONFIG101DEFAULT_OVERLAP_CONFIG101DEFAULT_FULL_DUPLEX_CONFIG101createTurnId114createUtteranceId114createParticipantId114TurnTakingManager114InterruptionHandler114BackchannelGenerator114SpeechOverlapHandler114VoiceActivityDetector114 +35 moreVoice effects: VoiceFilter, VoiceModulation, SpeedAdjustment,
background-noise addition, with audio utils.
DEFAULT_VOICE_FILTER_CONFIG31DEFAULT_BACKGROUND_NOISE_CONFIG31DEFAULT_VOICE_MODULATION_CONFIG31DEFAULT_SPEED_ADJUSTMENT_CONFIG31VoiceFilter38createVoiceFilter38BackgroundNoiseAddition40createBackgroundNoiseAddition40VoiceModulation45createVoiceModulation45SpeedAdjustment47createSpeedAdjustment47Empathic voice synthesis adaptation with dynamic emotional mirroring and frustration de-escalation
Empathic voice synthesis (libs/iris/voice/empathic-synthesis):
EmotionalToneAdapter, ProsodyModulator, EmpatheticMirroring,
DynamicToneShift, FrustrationDeescalation, composed as
EmpathicSynthesisEngine.
EmotionalToneAdapter5ProsodyModulator6EmpatheticMirroring7DynamicToneShift8FrustrationDeescalation9EmpathicSynthesisEngine10DEFAULT_EMOTIONAL_TONE_ADAPTER_CONFIG12DEFAULT_PROSODY_MODULATOR_CONFIG12DEFAULT_EMPATHETIC_MIRRORING_CONFIG12DEFAULT_DYNAMIC_TONE_SHIFT_CONFIG12DEFAULT_FRUSTRATION_DEESCALATION_CONFIG12Voice-first journaling: VoiceJournalRecorder, JournalTranscription,
JournalSummarization, JournalSearch (semantic/keyword).
DEFAULT_VOICE_JOURNAL_RECORDER_CONFIG32DEFAULT_JOURNAL_TRANSCRIPTION_CONFIG32DEFAULT_JOURNAL_SUMMARIZATION_CONFIG32DEFAULT_JOURNAL_SEARCH_CONFIG32mapTranscriptSegments32VoiceJournalRecorder40createVoiceJournalRecorder40JournalTranscription42createJournalTranscription42JournalSummarization44createJournalSummarization44JournalSearch46createJournalSearch46Pronunciation correction: PronunciationDetector, custom-pronunciation
dictionary, PronunciationFeedback, AccentAdaptation.
DEFAULT_PRONUNCIATION_DETECTOR_CONFIG24DEFAULT_ACCENT_ADAPTATION_CONFIG24CustomPronunciationDictionary29createCustomPronunciationDictionary29normalizePronunciationWord29AccentAdaptation35createAccentAdaptation35PronunciationDetector37createPronunciationDetector37PronunciationFeedback39createPronunciationFeedback39Text-to-speech synthesis system with real-time TTS, voice selection, prosody control, and streaming synthesis
Text-to-speech (~20 modules): a SpeechSynthesizer with voice selection,
prosody/emotion control, and streaming, plus concrete
ElevenLabs/Cartesia/local/persona provider sub-modules, composed as
SynthesisSystem.
VoiceId14AudioChunkId14createSynthesisSessionId14createVoiceId14createAudioChunkId14SampleRate14AudioOutputConfig14DEFAULT_AUDIO_OUTPUT_CONFIG14SynthesizedAudioChunk14WordTiming14VoiceAge14VoiceStyle14VoiceQuality14VoiceProvider14 +98 moreSub-100ms streaming TTS pipeline with speculative preloading and dynamic quality-latency tradeoffs
Ultra-low-latency voice (~18 modules): a StreamingTTSPipeline,
AudioBufferPreloader, LatencyMonitor, full-duplex interruption handling,
endpointing/turn-taking/backchannel models, and a
VoiceActivityOptimizationEngine, composed as UltraLowLatencyVoiceEngine.
QualityLatencyTradeoff5AudioBufferPreloader6LatencyMonitor7HeuristicChunkSynthesizer8StreamingTTSPipeline9InterruptionDetector10GracefulStopGenerator11ContextPreserver12SeamlessResumption13FullDuplexInterruptionEngine14EndpointingModel15BackchannelGenerator16TurnTakingPredictor17SilenceClassifier18 +10 moreeverything else (23)#
Unmounted A2A-shaped compatibility prototype; not a conformant or deployable A2A implementation
Private, unmounted A2A-shaped compatibility prototype (libs/iris/a2a/src):
local agent-card, task-negotiation, and result-sharing experiments only. It is
not a current A2A implementation or interoperability claim. ADR-0091 defers
adoption until a named independent agent boundary exists.
A2ATaskId39A2AMessageId39A2AArtifactId39A2ASubscriptionId39createA2ATaskId39createA2AMessageId39createA2AArtifactId39createA2ASubscriptionId39DEFAULT_A2A_PROTOCOL_VERSION39A2ACapability39A2AHealthStatus39A2ATaskStatus39A2ATaskPriority39A2ATaskMessage39 +33 moreAction safety system for AI agents with validation, blocking, and audit logging
Action-safety system for agents: ActionValidator, DangerousActionBlocker,
confirmation workflow, undo capability, and audit log, composed as
SafetySystem.
RuleId14AuditEntryId14ConfirmationId14UndoOperationId14SafetySessionId14createRuleId14createAuditEntryId14createConfirmationId14createUndoOperationId14createSafetySessionId14ActionType14RiskLevel14ActionDescriptor14ActionContext14 +53 moreAmbient intelligence system with background monitoring and anomaly detection
Ambient intelligence (proactive): BackgroundMonitor, AnomalyDetector,
OpportunityIdentifier, RiskAwareness, AlertManager, composed by
AmbientIntelligenceSystem.
BackgroundMonitor14createBackgroundMonitor14AnomalyDetector15createAnomalyDetector15OpportunityIdentifier16createOpportunityIdentifier16RiskAwareness17createRiskAwareness17AlertManager18createAlertManager18AmbientIntelligenceSystem46UserAnalysisResult254createAmbientIntelligenceSystem266Anticipatory-assistance engine (~30 modules) — pattern recognition, context triggers, relevance scoring, need/task prediction, productivity-awareness (break/timing/focus), and opportunity detection — the largest proactive lib.
DEFAULT_ENGINE_CONFIG96createPatternId102createSuggestionId102createTriggerId102createUserId102createContextId102PatternRecognizer114createPatternRecognizer114ContextTrigger120createContextTrigger120RelevanceScorer126createRelevanceScorer126SuggestionPresenter132createSuggestionPresenter132 +28 moreSpecialized agent archetypes for common task domains
Specialized agent archetypes (libs/iris/agents/archetypes) —
Research/Code/Data/Creative/ Operations agents (aliased
Researcher/Coder/Analyst/Writer/Operator) over a base-archetype.ts, with an
ArchetypeRegistry and createArchetypeWithPersona. Includes real
research-nlp.ts, web-search-provider.ts, command-runner.ts helpers.
TemplateId15createArchetypeId15createTemplateId15ResearchSpecialization15CodeSpecialization15DataSpecialization15CreativeSpecialization15OperationsSpecialization15PersonaConfig15CommunicationStyle15LanguagePreferences15ToolPreferences15BehaviorConfig15SearchSettings15 +115 moreAutomation proposals system for identifying, suggesting, recording, and executing automations
Workflow-automation proposals: PatternBasedAutomation, AutomationSuggester,
WorkflowRecorder, WorkflowManager, executed by AutomationSystem.
createWorkflowId84createPatternId84createSuggestionId84createUserId84createExecutionId84PatternBasedAutomation100createPatternBasedAutomation100AutomationSuggester102createAutomationSuggester102WorkflowRecorder104createWorkflowRecorder104AutomationExecutor106createAutomationExecutor106valuateCondition106 +5 moreDatabase tools for AI agents with safe query execution and exploration
Database tools for agents: QueryValidator, QueryBuilder, DatabaseBrowser,
ResultFormatter, and a SQLQueryTool over a DatabaseExecutor seam (with a
mock executor for tests).
ConnectionId14TableName14ColumnName14createQueryId14createConnectionId14createTableName14createColumnName14DatabaseConnectionConfig14ConnectionStatus14ConnectionInfo14AccessMode14ParameterValue14QueryParameters14QueryOptions14 +53 moreQuarantined simulated desktop prototype for tests; not a production or Eve runtime
Desktop application automation: DesktopController, WindowManager,
MenuNavigator, DialogHandler, ShortcutExecutor, wrapped by
DesktopAutomationAgent.
WindowId15ApplicationId15ProcessId15MenuItemId15DialogId15createWindowId15createApplicationId15createProcessId15createMenuItemId15createDialogId15WindowState15WindowLayer15ApplicationState15WindowInfo15 +51 moreEnsemble voting and consensus building for multi-model AI decisions
Multi-model ensemble: VotingStrategy, ConsensusBuilder,
DisagreementResolver, composed as EnsembleOrchestrator.
createEnsembleId64createEnsembleMember64DEFAULT_VOTING_CONFIG64DEFAULT_RESOLUTION_CONFIG64DEFAULT_ENSEMBLE_CONFIG64MajorityVotingStrategy73PluralityVotingStrategy73WeightedVotingStrategy73ConfidenceWeightedVotingStrategy73RankedChoiceVotingStrategy73UnanimousVotingStrategy73SupermajorityVotingStrategy73BordaCountVotingStrategy73createVotingStrategy73 +9 moreAutomatic failover and resilience system for the Iris conversation system
Automatic failover for provider integrations: HealthChecker, CircuitBreaker,
RetryPolicy, FallbackChain, composed as FailoverManager.
createFailoverId51DEFAULT_HEALTH_CHECKER_CONFIG51DEFAULT_RETRY_POLICY_CONFIG51DEFAULT_FALLBACK_CHAIN_CONFIG51createDefaultFailoverConfig51HealthChecker60createHealthChecker60RetryPolicy63createRetryPolicy63createAggressiveRetryPolicy63createConservativeRetryPolicy63createRateLimitRetryPolicy63DEFAULT_CIRCUIT_BREAKER_CONFIG80CircuitBreaker80 +13 moreTool learning system for AI agents - parsing docs, inferring parameters, and optimizing usage patterns
Tool-learning system: ToolDocParser (OpenAPI/TypeScript),
ParameterInference, UsagePatternOptimizer, dynamic tool registration, plus a
real TDigest/PercentileTracker.
DEFAULT_LEARNING_CONFIG122DEFAULT_TOOL_CONFIG122ToolDocParser125createToolDocParser125ParameterInference126createParameterInference126UsagePatternOptimizer127createUsagePatternOptimizer127ToolRegistrationManager128createToolRegistrationManager128TDigest129PercentileTracker129createTDigest129LearningTools163 +1 moreMCP (Model Context Protocol) client for multi-model AI systems
Model Context Protocol client: MCPClient with tool discovery, resource access,
and prompt templates for connecting to MCP servers.
createMCPSessionId89createMCPRequestId89DEFAULT_PROTOCOL_VERSION89DEFAULT_CLIENT_CONFIG89MCPToolSchema89MCPResourceSchema89MCPPromptSchema89MCPToolCallSchema89MCPError89MCPConnectionError89MCPTimeoutError89MCPClient108createMCPClient108createHTTPClient108 +28 moreIntelligent model routing and selection for the Iris conversation system
Intelligent model routing/selection: TaskClassifier, CostOptimizer,
LatencyOptimizer, QualityEstimator, and configurable RoutingPolicy,
composed as ModelRouter (with balanced/cost presets).
ModelRouter36createModelRouter36createCostOptimizedRouter36createQualityOptimizedRouter36createLatencyOptimizedRouter36createBalancedRouter36TaskClassifier49createTaskClassifier49getTaskProfiles49getTaskProfile49CostOptimizer60createCostOptimizer60stimateCost60findCheapestModel60 +23 moreMulti-agent orchestration and coordination for AI agents
Multi-agent orchestration (~22 modules): AgentSpawner, InterAgentMessaging,
TaskDistributor, ResultAggregator, SharedContext, plus
consensus/negotiation/ handoff/conflict protocols and an orchestrator.
AgentInstanceId13MessageId13TaskId13SubtaskId13ResultId13createAgentInstanceId13createMessageId13createTaskId13createSubtaskId13createResultId13AgentStatus13AgentCapability13AgentConfig13AgentInstance13 +133 moreShared-memory collaboration for multi-agent systems: in-memory
SharedAgentMemory, MemoryBroadcast, selective-sharing policy, and
memory-conflict resolution.
DEFAULT_SHARED_AGENT_MEMORY_CONFIG38DEFAULT_MEMORY_BROADCAST_CONFIG38DEFAULT_SELECTIVE_MEMORY_SHARING_CONFIG38DEFAULT_MEMORY_CONFLICT_RESOLUTION_CONFIG38SharedAgentMemory45createSharedAgentMemory45MemoryBroadcast47createMemoryBroadcast47SelectiveMemorySharing49createSelectiveMemorySharing49MemoryConflictResolution54createMemoryConflictResolution54Plugin architecture for extending Iris AI platform
Plugin architecture (~17 modules): PluginRegistry, PluginLifecycleManager,
PluginSandbox, UI-extension/integration managers, and a plugin workflow
engine, composed as PluginSystem.
PluginSystem112createPluginSystem112getGlobalPluginSystem112resetGlobalPluginSystem112PluginRegistry124createPluginRegistry124PluginLifecycleManager131createLifecycleManager131PluginSandbox138createPluginSandbox138UIExtensionManager145createUIExtensionManager145getGlobalUIExtensionManager145resetGlobalUIExtensionManager145 +8 moreExtended thinking and chain-of-thought reasoning for Iris AI
Extended-thinking / chain-of-thought: ThinkingMode, ReasoningChain,
ThoughtValidator, ThinkingBudget, and a thinking-summary generator.
StepId32ChainId32createThinkingId32createStepId32createChainId32ReasoningStepType32ValidationStatus32ConfidenceLevel32ThinkingPriority32ThinkingCost32ThinkingTiming32ReasoningStep32ReasoningChain32ChainValidation32 +41 moreSchedule-aware reminder system with calendar integration and smart timing
Schedule-aware reminders: SmartTiming, DeadlineTracker, calendar
integration/sync, and a multi-channel ReminderEngine with a DeliveryProvider
seam.
createReminderId100createCalendarEventId100createDeadlineId100createUserId100createCalendarId100createNotificationId100DEFAULT_ENGINE_CONFIG113DEFAULT_TIMING_PREFERENCES113SmartTiming119createSmartTiming119CalendarIntegration121createCalendarIntegration121createCalendarEvent121DeadlineTracker127 +8 moreSandboxed execution environment for AI agents with isolation and resource limits
Sandboxed execution environment: ResourceManager (with TokenBucket),
NetworkController, FilesystemController, SnapshotManager, plus
SandboxEnvironment/ SandboxManager for isolated agent execution.
SnapshotId14ExecutionId14SandboxProcessId14createSnapshotId14createExecutionId14createSandboxProcessId14IsolationLevel14SandboxInfo14SandboxProcessInfo14ResourceUsage14ResourceViolation14NetworkRestrictions14NetworkConnection14FilesystemMount14 +30 moreStreaming APIs for Iris AI Assistant - SSE, WebSocket, and gRPC
Streaming APIs (libs/iris/platform/streaming): SSE, WebSocket, and a
gRPC-streaming abstraction behind a ProtocolFactory, composed as
StreamingManager with createStreamingClient.
StreamProtocol22BaseStreamProtocol22ProtocolFactory22ProtocolFactoryConfig22ProtocolEvents22SSEClient34SSEWriter34buildSSEHeaders34createSSEResponse34streamToSSE34SSEMessage34SSEClientEvents34WebSocketClient48WebSocketServer48 +31 moreWhite-label customization support for Iris AI platform
White-label customization (~24 modules): brand/theme/voice-persona/deployment
builders + managers, a component registry, preset themes/voices, custom-domain
support with a dns-resolver and ssl-provisioner.
WhiteLabelBuilder67createWhiteLabelBuilder67createWhiteLabelConfig67BrandBuilder77createBrandBuilder77createBrand77BrandManager77createBrandManager77getGlobalBrandManager77resetGlobalBrandManager77ThemeBuilder88createThemeBuilder88createThemeFromColor88ThemeManager88 +78 moreWorkflow orchestration for AI agent task sequences
Workflow orchestration (~17 modules): WorkflowEngine (with a TaskExecutor
seam), TaskDecomposer, DependencyGraph, ProgressTracker, ErrorRecovery,
parallel executor, plan visualizer.
TaskId15StepId15ExecutionId15CheckpointId15AgentInstanceId15createTaskId15createStepId15createExecutionId15createCheckpointId15TaskStatus15TaskPriority15ExecutionMode15RetryStrategy15TaskDefinition15 +82 morePython SDK (libs/iris/sdk/python): an iris_sdk package with
IrisClient, per-domain clients (agent/conversation/knowledge/memory),
http.py, typed types.py, and py.typed, packaged via pyproject.toml.
(Project name lacks the @iris/ prefix.)