ctx-sys
Knowledge graphs from codebases using AST parsing and semantic embeddings with vector, graph, and full-text search.
What it does
Knowledge graphs from codebases using AST parsing and semantic embeddings with vector, graph, and full-text search.
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.
Capabilities
Server
Quality
deterministic score 0.57 from registry signals: · indexed on pulsemcp · has source repo · 10 github stars · registry-generated description present