Local hybrid RAG system that indexes codebases and serves context through an MCP server. Uses Tree-sitter AST parsing for precise entity extraction across TypeScript, Python, Rust, Go, Java, C/C++, and C#. Combines vector search, full-text search (FTS5), and graph traversal with reciprocal rank fusion for result ranking. Stores everything in a single SQLite instance with local Ollama embeddings, ensuring code never leaves the machine. Includes session management, architectural decision logging, and cross-session learning.
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.