OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Code Graph Rag

An MIT-licensed, open-source developer tool that combines multi-language code parsing, a Memgraph knowledge graph and retrieval-augmented natural-language interaction.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Code Graph Rag — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when code relationships, architectural context or repository-aware editing matter more than plain text search.

Who it is for

  • Developers exploring large or mixed-language repositories.
  • Teams working with monorepos and cross-file code relationships.
  • Users seeking repository-grounded code search, analysis or editing.

Documented uses

  • Index source files and relationships into a code knowledge graph.
  • Ask natural-language questions about repository structure.
  • Retrieve functions, classes and methods by name or intent.
  • Identify dead code and inspect runtime-observed calls.
  • Apply AST-based edits with a preview of the resulting diff.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The tool is available as a Python package through PyPI and is documented for CLI, self-hosted and server use.

  • Memgraph is the documented knowledge-graph backend.
  • Tree-sitter provides the backbone, with optional compiler-grade frontends for selected ecosystems.
  • Runtime tracing can add observed call relationships, but only for code that ran.
  • Language support is tiered rather than uniform across all listed languages.
  • MCP integration is identified as likely compatible, but no tested client configuration is documented.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Code Graph Rag and index a repository

Set up the command-line tool and create or update a knowledge graph from a repository.

Before you start

  • A Python environment with uv or pipx.
  • The documented treesitter-full and semantic package extras.
  • A repository to index.
  • Memgraph is used as the knowledge-graph store.

Steps

  1. Install the package with uv using code-graph-rag[treesitter-full,semantic], or install the same package with pipx.

  2. Run cgr start --update-graph to parse the repository and update its knowledge graph.

  3. Run cgr start to enter the documented natural-language querying and editing workflow.

Expected outcome

The repository is represented in a Memgraph knowledge graph and is available to the interactive CLI for questions and code edits.

Guide limitations

  • The evidence does not document environment-specific configuration, model setup or a complete execution example.
  • Language capability varies: some languages have full support, while others have structural ast-grep support or remain in development.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Code Graph RagIndex source files and relationships into a code knowledge graph.CLI, Self-hosted, ServerThe repository is public and MIT-licensed. The tool is available as a Python package through PyPI and is documented for CLI, self-hosted and server use.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
vitali87/code-graph-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction