Provides local memory storage and retrieval for AI agents using vector embeddings generated by Ollama models. Stores memories as vectors in a Zvec database with metadata including workspace keys, memory types (decisions, preferences, facts, etc.), importance scores, and timestamps. Features semantic search, memory superseding for updates, workspace isolation, and automatic relevance scoring based on embedding similarity and importance weights. Designed for agents that need persistent memory across conversations without relying on external cloud services.
Cognium trust score
95%
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.