A control plane for managing AI agent companies with persistent conversations, global and project-scoped agent memory, per-agent tool assignment, skills selection, performance KPIs, and a self-improvement loop. Fork of paperclipai/paperclip with added memory persistence, tool discovery, and analytics dashboard. Built with TypeScript and deployable via Docker.
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.