GeezerVison

The World Wide Web, restored to 800 pixels of glory.

GeezerVison is showing code-graph-rag.com — Code-Graph-RAG - AI-Powered Codebase Analysis

Open Source · 14 Languages · AI-Powered

Understand Any Codebase with AI-Powered Knowledge Graphs

Build comprehensive knowledge graphs from multi-language codebases using Tree-sitter parsing. Query, edit, and optimize your code with natural language.

View on GitHub Enterprise Solutions

code-graph-rag

$ uv tool install "code-graph-rag[treesitter-full,semantic]"

$ cgr daemon up

✓ Memgraph + Qdrant running

$ claude mcp add code-graph-rag

✓ MCP server added successfully

$ Ask: "What functions handle authentication?"

Querying knowledge graph...

Found 3 functions across 2 files:

→ auth/login.py:authenticate_user (line 42)

→ auth/login.py:verify_token (line 87)

→ auth/middleware.py:require_auth (line 15)

Core Capabilities

Everything you need to understand your code

From parsing to optimization, Code-Graph-RAG provides a complete toolkit for codebase intelligence.

Multi-Language Parsing

Tree-sitter based AST parsing across 14 languages with unified graph schema for functions, classes, modules, and dependencies.

Knowledge Graph

Build interconnected graphs of your codebase structure — functions, classes, imports, and call relationships stored in Memgraph.

Natural Language Queries

Ask questions about your codebase in plain English. AI translates your intent into precise Cypher graph queries.

AI Code Editing

Surgical code replacement with AST-based function targeting, visual diff previews, and exact code block modifications.

Code Optimization

AI-powered codebase optimization with language-specific best practices and interactive approval workflow.

Structural Search & Replace

Match and rewrite code by AST pattern with ast-grep — structure-aware find and replace across the whole codebase, not text or regex.

Data-Flow Tracing

FLOWS_TO taint edges follow values from sources through assignments, calls, and returns to I/O sinks — provenance as graph reachability.

Dead Code Detection

Walk call and reference edges from entry points to surface unreachable functions and methods, with a CI-friendly failure mode.

MCP Integration

Works as an MCP server with Claude Code. 15 tools for indexing, querying, editing, and searching directly from your IDE.

Enterprise Services

Open source core, enterprise-grade support

Code-Graph-RAG is free and open source. For teams that need more, we offer dedicated support, consulting, and custom development.

Custom Knowledge Graph Relationships

Define bespoke edge types and relationship semantics tailored to your organization — going far beyond standard code relationships. Model compliance mappings, data lineage, team ownership, cost attribution, and domain-specific connections that turn your code graph into a strategic asset no competitor can replicate.

Compliance traceability — link code to regulatory requirements (SOX, HIPAA, PCI-DSS)
Data lineage & flow tracking across services and databases
Security classification — flag PII handlers & map blast radius
Team ownership & cost attribution at the code level

Cloud-Hosted & On-Prem Deployment

Fully managed cloud-hosted solutions for both the graph database and AI agent connection — zero infrastructure overhead. On-premise and air-gapped deployments also available for regulated environments.

Managed cloud graph DB & agent
On-premise deployment
Air-gapped environments

Custom Development

Tailored features, new language parser development, and workflow optimization built to your exact specifications.

Custom language parsers
Proprietary features
Performance tuning

Technical Support Contracts

Custom SLAs, priority issue resolution, and dedicated assistance from the team that builds Code-Graph-RAG.

Guaranteed response times
Direct access to core devs
Priority bug fixes

Integration Consulting

Expert guidance deploying Code-Graph-RAG in your infrastructure and integrating with your CI/CD, IDEs, and toolchain.

CI/CD pipeline setup
Custom toolchain integration
Workflow optimization

Training & Onboarding

Hands-on workshops to get your team productive fast — on-site or remote, customized to your stack and use cases.

On-site or remote
Custom training materials
Advanced usage patterns

View Plans & Pricing

Language Support

14 languages, one unified graph

Parse any codebase with Tree-sitter grammars, or add a language from a single ast-grep pattern file. Each language produces the same graph schema for consistent querying.

Python

Full

.py

Type inference ·Decorators ·Nested functions

TypeScript

Full

.ts, .tsx, .mts, .cts

Interfaces ·Type aliases ·Enums

JavaScript

Full

.js, .jsx, .mjs, .cjs

ES6 modules ·CommonJS ·Prototype methods

Rust

Full

.rs

Impl blocks ·Associated functions ·macro_rules! macros

Java

Full

.java

Generics ·Annotations ·Records

C

Full

Functions ·Structs ·Unions

C++

Full

.cpp, .h, .hpp, .cc, .cxx, .hxx, .hh, .ixx, .cppm, .ccm

Templates ·Lambdas ·C++20 modules

Lua

Full

.lua

Local/global functions ·Metatables ·Closures

C#

Full

.cs

Records ·Generics ·Typed call resolution with overloads

Go

Full

.go

Receiver methods ·Cross-file binding ·Structs & interfaces

PHP

Full

.php

Classes ·Interfaces ·Traits

Dart

Full

.dart

Mixins ·Extensions ·Factory constructors

Ruby

Structural

.rb

Modules ·Classes ·Methods

Scala

Dev

.scala, .sc

Case classes ·Objects ·Traits

See It In Action

Interactive codebase exploration

Watch Code-Graph-RAG parse a codebase, build a knowledge graph, and answer natural language queries in real-time.

Demo

Claude Code Integration

Works directly with Claude Code

Code-Graph-RAG runs as an MCP server, giving Claude Code 15 powerful tools to query, search, edit, and optimize your codebase using natural language.

Setup

# Install, then start the packaged Memgraph + Qdrant stack
uv tool install "code-graph-rag[treesitter-full,semantic]"
cgr daemon up

# Add Code-Graph-RAG as an MCP server in Claude Code
claude mcp add --transport stdio code-graph-rag \
  --env TARGET_REPO_PATH="$(pwd)" \
  --env CYPHER_PROVIDER=google \
  --env CYPHER_MODEL=gemini-2.5-flash \
  --env CYPHER_API_KEY=your-api-key \
  -- cgr mcp-server

Available MCP Tools

list_projects

List all indexed projects in the knowledge graph database

delete_project

Delete a specific project from the knowledge graph database

wipe_database

Completely wipe the entire database, removing all indexed projects

index_repository

Parse and ingest the repository into the Memgraph knowledge graph

update_repository

Incrementally update the repository without clearing existing data

query_code_graph

Query the codebase knowledge graph using natural language

get_code_snippet

Retrieve source code for a function, class, or method by qualified name

surgical_replace_code

Surgically replace an exact code block in a file

read_file

Read file contents with pagination for large files

write_file

Write content to a file, creating it if needed

list_directory

List contents of a directory in the project

semantic_search

Intent-based function search using embeddings with similarity scores

structural_search

Search code by AST pattern with ast-grep syntax, not text or regex

structural_replace

Rewrite code by AST pattern, with a dry-run diff before writing changes

ask_agent

Ask the full RAG agent a question about the codebase

5,349

Stars

710

Forks

Verified

OpenSSF Best Practices & Scorecard

Ready to understand your codebase?

Get started with the open-source community edition or contact us for enterprise solutions.

View on GitHub Contact for Enterprise

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.