Provides context-aware skill selection for AI agents, reducing token usage by 85-98% and improving accuracy through semantic retrieval, session memory, and feedback learning.
Enables AI agents to intelligently match tasks to skills through semantic embeddings, track skill effectiveness, detect skill gaps, and discover new skills from external sources.
Routes SKILL.md libraries to any MCP client, enabling task matching and skill loading with embedding-based scoring, keyword fallback, and context-window discipline.
A local-first skill runtime for AI coding agents that defines skills as verifiable, composable units with sandboxed execution, and exposes them as MCP tools over HTTP.