workflowstacks
ai-agent

codegraph: Faster AI Coding with a Live Code Knowledge Graph

Instantly tap a pre‑indexed, auto‑syncing code graph to cut tokens and tool calls, ideal for founders using Claude, Codex, Gemini, Cursor and more. 72k+ GitHub stars.

From the repo · “Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local”

74,707 stars+530★ this week4,834 forksTypeScriptGuide quality 8/10 · reviewed Sep 29Updated 10/22/2026100% free · open source
What it does

Codegraph leverages AI to provide instant code knowledge and insights for efficient development, helping startup founders navigate complex codebases

When to use it
  • •When trying to understand a large, unfamiliar codebase
  • •When needing to optimize code for better performance
  • •When looking to reduce development time by leveraging AI-powered code insights
Ready-to-paste prompt
npx codegraph --codebase ./myproject --model gpt3 --output insights.json
Heads up: Ensure you have a compatible version of Node.js (14.x or higher) and a GitHub token configured for authentication, as specified in the Codegraph README
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/codegraph && curl -fsSL https://workflowstacks.com/api/skills/codegraph/claude-skill -o ~/.claude/skills/codegraph/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How codegraph: Faster AI Coding with a Live Code Knowledge Graph works
Codeflow
Free to inspect

Codegraph: Faster AI Coding with a Live Code Knowledge Graph is a very large C project (~120k lines across 316 code files, plus 288 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~120k lines · 316 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
No API keys detected
C 89%TypeScript 8%Rust 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    src/index.ts
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
What's in each folder
src/Core code — the actual logic209 files
site/Frontend / UI31 files
docs/Documentation53 files
scripts/Helper scripts68 files
codegraph-kernel/Folder50 files
telemetry-dashboard/Folder21 files
telemetry-worker/Folder13 files
__tests__/Tests — proof it works301 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
colbymchenry
Language
TypeScript
Category
ai-agent
Published
1/18/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/codegraph.svg)](https://workflowstacks.com/skills/codegraph?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Brave Search MCP config

Give Claude live web search via the Brave Search API.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,577
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,154
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,161
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 91,588
OpenHands: Accelerate AI‑Powered Development for Founder Teams
Leverage OpenHands to build, test, and iterate AI agents with a single CLI, letting tech founders prototype smarter tools faster. 90k+ GitHub stars.
ai-agent★ 5,864
AReaL: Accelerate LLM Agent Development with Reinforcement Learning
AReaL lets founders integrate RL into LLM‑based agents quickly and flexibly, streamlining complex reasoning workflows. Ideal for Python teams building intelligent automation.
ai-agent★ 1,473
git-lrc: Instant AI Code Reviews on Every Commit
Get quick, AI‑powered micro reviews on each commit, helping founders ship cleaner code faster. 1.5k+ GitHub stars. Perfect for Go teams using VS Code.