Provides long-term semantic recall for AI agents through an embedded Kuzu graph database. Stores errors, solutions, concepts, and session histories with hybrid search combining semantic similarity, recency, context richness, and keyword matching. Supports 25+ tools across projects, sessions, error tracking, knowledge management, artifacts, and analytics. Runs fully local with no cloud dependencies.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
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.