Provides persistent memory for AI agents using a three-layer retrieval system combining SQLite storage, pgvector semantic search, and Neo4j entity graph traversal. Results are ranked using Reciprocal Rank Fusion for token-efficient recall at 300-500 tokens per query. Supports contradiction detection, entity timeline tracking, and runs fully locally via Docker with integrations for Claude Code, Cursor, and direct Python library usage.
Cognium trust score
0%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.