RadarTopicsBuildersWeeklyReads
Open Source Radar
vitali87/

code-graph-rag

GitHubWebsite

Code-Graph-RAG reads a multi-language codebase, builds a Memgraph-backed knowledge graph via Tree-sitter, and enables querying, editing, and optimization of code using natural language and AST-based patches.

2.5kstars
413forks
42issues
MITlicense
2025since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.

How it works

Two components:

  1. Multi-language parser: Tree-sitter based parser ingests functions, classes, methods, modules, and relationships into Memgraph.
  2. RAG system (codebase_rag/): An interactive CLI that turns natural language into Cypher queries, retrieves matching code, and drives AI-powered editing and optimisation.

Source Code -> Tree-sitter Parser -> AST Analysis -> Memgraph Knowledge Graph | User Query -> AI Model (Cypher Gen) -> Cypher Query -> Graph Results -> Response

See Architecture Overview and Graph Schema for details.

Getting started

Installation is PyPI-based. Install with extras:

# with uv (recommended)
uv tool install "code-graph-rag[treesitter-full,semantic]"

# or with pipx
pipx install "code-graph-rag[treesitter-full,semantic]"

You also need Docker (for Memgraph), cmake, and ripgrep. Full prerequisites and environment setup are in the Installation guide.

Quick Start:

# Start the packaged Memgraph + Qdrant stack (no compose file needed)
cgr daemon up

# Parse a repository into the graph, then query it
cgr start --repo-path /path/to/repo --update-graph --clean
cgr start --repo-path /path/to/repo

Recent releases

Latest 5 releases include:

  • v0.0.534 (2026-08-02): Automated tagging and release generation improved with enhanced workflow triggering; Docker build process updates include Git installation in the Docker builder stage.
  • v0.0.484 (2026-07-23): Cross-project endpoint linking resolving client request URLs to server routes across projects; gateway and proxy prefix rewrites; options-object routing.
  • v0.0.421 (2026-07-21): C# enhancements to Roslyn frontend with exact overloads, extension binding, and LINQ query call fixes.
  • v0.0.345 (2026-07-14): Security update addressing path traversal vulnerability in MCP read_file tool; C++ frontend updates.
  • v0.0.246 (2026-07-07): Binary support via PyInstaller; CI improvements including a binary smoke-test.

Traction

Stars: 2510 Forks: 413 Open issues: 42

License

MIT

Getting started (concise commands)

uv tool install "code-graph-rag[treesitter-full,semantic]"
# or with pipx
pipx install "code-graph-rag[treesitter-full,semantic]"
# Start the packaged Memgraph + Qdrant stack (no compose file needed)
cgr daemon up

# Parse a repository into the graph, then query it
cgr start --repo-path /path/to/repo --update-graph --clean
cgr start --repo-path /path/to/repo
SharePost on XLinkedIn
All trending reposRevenue-verified startups →