Combines HNSW vector search, reasoning-based tree retrieval, and BM25 keyword matching into a single retrieval platform using reciprocal rank fusion. Provides purpose-built agent memory with episodic, semantic, procedural, and shared memory types for multi-agent systems. Includes a RAG pipeline for document ingestion, chunking, and LLM-ready context building, all local-first with zero external dependencies.
Cognium trust score
62%
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 2026-09-02.
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.