Local repo-intelligence MCP for coding agents: indexes source, symbols, call graphs, git/GitHub history, and source-bound repo memories into local database.
Embeds your codebase into a local vector and graph database and exposes it as an MCP tool, enabling AI assistants to perform fast semantic search over your code using Graph RAG.
Enables agents to build and query code knowledge graphs for repositories in a folder — finding shortest paths between concepts, explaining concepts with neighbours and community context, and visualizing per-repo graphs through MCP tools.
Deterministic code-graph (GraphRAG) over your repo for LLM agents — local-first, git-native, zero-infra, served via MCP. Python, TS/JS, Rust, Go, Java, C#.
Local repository intelligence MCP server that builds a reusable graph of code structure for AI coding agents, providing 34 network-free tools for understanding, searching, and analyzing repositories without data leaving the machine.