Provides a two-layer memory system with short-term message storage and long-term extracted knowledge backed by a vector-indexed knowledge graph. The context engine runs before every AI response, combining time-ordered recent messages, semantic search across both memory layers, and graph-based memory ranking to inject relevant context. Ships as an MCP server, OpenClaw plugin, Next.js dashboard, and Convex-backed multi-tenant cloud service. Published on npm as crystal-memory.
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.