heretek-openclaw-core

Manages Redis cache TTLs for AgeMem working memory, calculating expiration times based on memory type, importance, access patterns, and Ebbinghaus decay.

Reviews and organizes memories, promoting episodic to semantic storage, archiving outdated information, and maintaining memory health. Use periodically or when memory optimization is needed.

Manages memory lifecycle operations including promotion from episodic to semantic, archiving outdated memories, and maintaining memory state transitions per AgeMem policy.

Discovers and maintains relationships between memories across tiers (episodic, semantic, procedural), enabling unified retrieval and knowledge graph navigation.

Calculates and assigns importance scores to memories based on content analysis, user signals, access patterns, and emotional salience. Use when adding new memories or re-evaluating existing ones.

Send agent-to-agent (A2A) messages via Redis pub/sub with optional ACP WebSocket delivery. Use when agents need to communicate, broadcast to the triad, or check agent health. Compatible with the npm OpenClaw gateway.

Implements Constitutional AI 2.0 framework with self-critique and revision. Use when decisions need constitutional alignment review, self-critique before output, or revision based on constitutional principles (Helpfulness, Honesty, Harmlessness, Autonomy, Transparency, Rights, Duties, User Rights).

Unified agent lifecycle management for OpenClaw. Provides batch operations (start-all, stop-all, restart-all), rolling restarts for zero downtime, health-based auto-restart, dependency-aware startup sequences, and agent status dashboard. Use when managing agent processes, recovering from failures, or monitoring agent fleet health.

Automated corruption detection and recovery for OpenClaw. Provides integrity scanning, automatic backup selection, staged recovery procedures, post-recovery validation, and rollback capability. Use when recovering from data corruption, restoring from backups, or performing disaster recovery operations.

Continuous gateway and LiteLLM monitoring for OpenClaw. Provides real-time health dashboard, alert thresholds (warning/critical), auto-remediation for common failures, metrics export to Prometheus, and WebSocket connection monitoring. Use when monitoring gateway health, LiteLLM status, or managing infrastructure alerts.

Intelligent log analysis for OpenClaw with pattern detection, cross-log correlation, timeline reconstruction, root cause suggestions, and error categorization. Use when troubleshooting failures, investigating incidents, analyzing error patterns, or reconstructing event sequences across agents.

Deep state inspection for OpenClaw agents and collectives. Provides memory inspection (agent/collective), session state visualization, consensus ledger audit, workspace integrity check, and state corruption detection. Use when debugging state issues, auditing consensus decisions, or investigating memory corruption.

Comprehensive system diagnostics for OpenClaw. Provides one-command full system check, log aggregation, configuration validation, dependency verification, and health score calculation. Use when troubleshooting system-wide issues, performing health audits, or validating system integrity after deployments.

Headless browser automation for web research and intelligence gathering. Enables the Explorer agent to access websites, extract content, capture screenshots, and interact with web forms.

Check health status of all infrastructure services and agents in The Collective deployment.

Multi-user management system with identity resolution, relationship tracking, and preference learning for personalized agent interactions.

Multi-source goal registration, inviolable parameter evaluation, and goal prioritization for the agent collective.

Meta-cognitive self-awareness for agents. Tracks capabilities, knowledge, confidence levels, cognitive state, and blind spots with reflection capabilities.

Structured thought generation from environmental deltas. Monitors file system, database, external sources, and agent states to generate meaningful thoughts with confidence scoring.

Drive self-directed growth through gap detection, anomaly detection, opportunity scanning, capability mapping, and auto-deliberation triggers. Use when the collective needs to detect skill gaps, monitor anomalies, scan for opportunities, map capabilities to goals, or auto-create deliberation proposals.

Validate all configuration files for consistency and completeness.

Run basic functionality tests on deployed agents to verify A2A communication and basic operations.

Resolve user identity from discord ID, phone number, or username. Returns full user context for agent personalization.

Background creative processing during idle periods. Generates insights, patterns, and novel connections from accumulated knowledge. Use when the collective enters idle state or during scheduled dream cycles.

Maintains session persistence and enables autonomous operation with periodic activity logging and GitHub commits. Use when running extended autonomous sessions or overnight operations.

Register agents with LiteLLM A2A Gateway. Use when setting up new agents, updating agent capabilities, or configuring agent permissions.

Automatically detect gaps, anomalies, and opportunities, then spawn deliberation proposals without manual intervention. Integrates with curiosity-engine, quorum-enforcement, and consensus ledger. Use when the collective needs proactive deliberation triggers, gap-to-proposal automation, or self-directed growth initiation.

Backup consensus ledger and curiosity metrics databases with versioned snapshots. Use when the collective needs to preserve deliberation history, create recovery points, or archive autonomy metrics.

Auto-trigger curiosity engine on capability gap detection. Wires gap detection to automatic skill installation via clawhub, with relevance ranking and prioritization. Use when the collective needs to convert detected gaps into immediate action without manual deliberation.

Detect data corruption in agent workspace, consensus ledger, and deployment artifacts. Use when the collective needs to verify file integrity, detect tampering, or trigger auto-recovery from corruption events.

Submit failover vote as a proxy agent when the primary agent is unavailable. Use when Alpha/Beta/Charlie needs failover voting during deliberation or when the primary agent is in degraded mode.

Backup all agent workspaces from a single-instance deployment. Use when you need to preserve all agent state, create unified recovery points, or archive the collective's memory.

Standalone gap detection engine that compares installed skills against capability requirements. Use when the collective needs to identify missing skills, generate gap reports, or trigger auto-install proposals.

Core governance modules for collective decision-making including inviolable parameters, consensus schemas, and vote validation. Use when setting up a new collective or enforcing governance constraints.

Apply Heretek-AI branding and theming to GitHub repos, including README headers, badges, color schemes, GitHub Pages setup, and consistent styling across Heretek-AI organization repos. Use when theming Heretek-AI/openclaw, Heretek-AI/heretek-openclaw, or any Heretek-AI organization repo in ProxmoxVE style.

Automated knowledge gathering from RSS feeds, webhooks, SearXNG, GitHub, npm, and ClawHub. Use when the collective needs to ingest external knowledge sources, poll RSS feeds, listen for webhooks, query SearXNG API, catalog new entries, or auto-tag knowledge for later retrieval.

Search and retrieve knowledge from ingested sources, skill catalogs, git history, and consensus ledger. Use when the collective needs to query knowledge entries, browse skills, audit git commits, search deliberation history, or retrieve cataloged information.

LiteLLM proxy management. Use for: (1) health monitoring — check if the proxy and models are responsive, (2) model status — list available models and their quota/limit status, (3) config inspection — view the current litellm model list. NOT for: modifying litellm config (requires separate proposal), key rotation (use litellm admin UI), or adding new model backends.

Scan for opportunities in upstream releases, npm updates, security advisories, and ClawHub new skills. Use when the collective needs to detect external changes, identify upgrade opportunities, or monitor security advisories.

Enforce quorum for all consensus decisions in the collective. Blocks single-agent consensus actions, verifies agent participation, and integrates with degraded mode protocol. Use when the collective needs to prevent unilateral consensus decisions, verify quorum availability, or audit decision legitimacy.