This knowledge graph memory server enables persistent memory and error tracking for AI assistants using a local graph structure. It provides tools for creating, querying, and updating entities, relations, and observations, as well as a lesson system for capturing and retrieving solutions to encountered errors. The implementation features transactional operations, file management for scalability, and caching for improved performance. Developed by Anthropic, it's designed to enhance AI assistants' contextual understanding and problem-solving capabilities across conversations and tasks.
Cognium trust score
92%
Tier
Verified
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.