LibreAI / Dev Tools / CodeGraphContext
// devtools · CodeGraphContext/CodeGraphContext

CodeGraphContext

CodeGraphContext is an open-source dev tools project by CodeGraphContext (CodeGraphContext/CodeGraphContext on GitHub). It has 4,242 GitHub stars and 832 forks, is released under the MIT license, and was last updated on GitHub on 29 September 2026.

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

★ 4.2k stars⑂ 832 forksMITupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
4,242
Forks
832
License
MIT
Last updated on GitHub
29 September 2026
Category
Dev Tools
Listing
Full install guide
Official site
Official site
// how it works

How it works

  1. Install it

    Package managers, install scripts, or app stores on every OS.

  2. Configure lightly

    Sane defaults work; dotfiles make it yours.

  3. Learn the keys

    A weekend of muscle memory pays off for years.

  4. Extend it

    Plugins and themes from huge community ecosystems.

// features

Why people love it

Keyboard-first

Hands stay on keys; the mouse becomes optional.

Open & hackable

Customize prompts, tools, and behavior; no black box.

Diff-first workflow

Every change is a reviewable diff — you stay in control.

Model flexibility

Swap between frontier APIs and local models per task.

Terminal & IDE

Lives where you work: VS Code, JetBrains, Neovim, or plain terminal.

AI pair programming

Agentic coding assistants that plan, edit, and run commands.

Advertisement
// run it

Run it yourself

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/CodeGraphContext/CodeGraphContext.git
    cd CodeGraphContext
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project's launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// use cases

What you can build

  • Ship features faster with an AI pair programmer.
  • Refactor legacy code with confidence.
  • Onboard onto unfamiliar codebases.
  • Automate tests, docs, and chores.

Also on this shelf: latex-arxiv-SKILL — Agentic harness for writing arXiv-ready ML review papers with AI. Also on this shelf: livinity-io — an open-source, self-hostable "Cloud AI Computer" OS. The Dev Tools shelf also holds differ — a two-panel terminal UI for git diffs, with AI commits.

Advertisement
// faq

Questions, answered

Who maintains CodeGraphContext?

It is an open-source project at CodeGraphContext/CodeGraphContext with 832 forks. Check the repo's contributors and recent commits to see how active maintenance is.

Is CodeGraphContext free for commercial use?

MIT licensed — use it commercially, no strings attached.

Which editor does it support?

VS Code and terminal are universal; check each tool for JetBrains/Neovim.

Is my code sent anywhere?

With local models, no. With APIs, check the provider's retention policy.

Local or cloud models?

Cloud frontier models code best today; local keeps everything private and free.

// keep exploring

Similar tools

Productivity

natively-cluely-ai-assistant

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflie…

★ 2.7k starsUnknown
View guide →
Dev Tools

px0

px0 is an IDE built for reviewing AI-generated code, optimized for speed. It turns your browser into a zero-latency console with native Git and GitHub integr…

★ 1.8k starsMIT
View guide →
Dev Tools

kodus-ai

Open source, self-hosted AI code review. Bring your own LLM.

★ 1.4k starsUnknown
View guide →
Dev Tools

code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked con…

★ 31.9k starsMIT
View guide →
Dev Tools

ddgs

A Python metasearch library aggregating many web search services — plus CLI, API and MCP server

★ 3.0k starsMIT
View guide →
Dev Tools

ripwire

The ripgrep of AI context — a zero-dependency C++23 CLI + MCP server that maps your repo for coding agents

★ 2.4k starsApache-2.0
View guide →
// alternatives

Alternatives in Dev Tools

The most-starred other Dev Tools projects in the LibreAI catalogue — the realistic shortlist if CodeGraphContext is not the right fit.

  • OpenCode★ 211.6k

    The open source coding agent

  • Transformers★ 166.9k

    The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.

  • claude-code★ 149.7k

    Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase

  • cc-switch★ 141.3k

    Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents

  • codex★ 128.2k

    OpenAI's lightweight coding agent that runs locally in your terminal

// more in devtools

More in Dev Tools

Nearby Dev Tools projects in the catalogue, closest in stars to CodeGraphContext — keep exploring the shelf either side of it.

  • KiroCrew★ 4.3k

    KiroCrew: a persistent, self-improving workspace where AI dev crews keep working after you close the tab

  • skill-recorder★ 4.2k

    Skill Recorder: watch a human do a task once, then generate a reusable AI-agent skill from the recording

  • gptme★ 4.4k

    gptme is a terminal AI agent with shell, files, browser, vision, and subagents — provider-agnostic

  • claude-octopus★ 4.2k

    Claude Octopus orchestrates Claude, Codex, Copilot, Gemini, and Ollama on one task — and surfaces disagreement

  • judge0★ 4.5k

    Judge0 is a robust, scalable, open-source online code execution system with a simple HTTP API

  • zvec-grep★ 4.0k

    zvec-grep (zg): one local CLI unifying ripgrep-style exact search, BM25, and semantic vector search

Get CodeGraphContext

Free and open — grab the source, star the repo, and start creating.