RagCode transforms repositories into AI-ready codebases through semantic vector search, enabling understanding by meaning rather than keywords. Built in Go with support for Go, PHP (including Laravel), and Python codebases, it uses local Ollama for embeddings and Qdrant for vector storage to maintain complete privacy without external API calls. The server provides semantic search, hybrid search, function details retrieval, type definition lookup, and workspace indexing across multiple languages with automatic workspace detection and per-language collection management.
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.