FreePeak

FreePeak / LeanKG

Public

About Lightweight Knowledge Graph for AI-Assisted Development

12
0
100% credibility
Found Mar 27, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Rust
AI Summary

LeanKG is a local knowledge graph tool that indexes codebases to provide targeted, token-efficient context to AI coding assistants via an integration protocol.

How It Works

1
🔍 Discover LeanKG

You hear about a smart local helper that makes your AI coding buddy understand your entire project instantly.

2
📥 One-click install

Run a simple command tailored to your favorite AI tool like Cursor or Claude to set it up on your computer.

3
🏠 Add to your project

Place it in your code folder so it can learn about your files and how they connect.

4
✨ Scan your codebase

It quietly builds a map of your code's structure, functions, and links – all running safely on your machine.

5
🔗 Connect your AI

Your AI tool now talks to this map for quick, precise answers instead of guessing.

6
💬 Ask smart questions

Tell your AI 'What breaks if I change this?' or 'Where's that function?' and get spot-on results.

🎉 Code smarter, faster

Your AI gives laser-focused insights, saving time and effort while keeping everything private and speedy.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is LeanKG?

LeanKG builds a lightweight knowledge graph from your codebase, parsing Rust, Go, TypeScript, and Python files to map functions, imports, calls, and tests. It runs locally with minimal resources using Rust and exposes an MCP server so AI tools like Cursor, Claude Code, and OpenCode query targeted subgraphs instead of scanning everything—cutting context tokens from 10k+ to dozens. CLI commands like `leankg init`, `index ./src`, and `impact main.rs --depth 3` make setup and queries dead simple for ai-assisted development.

Why is it gaining traction?

Unlike heavy graph DBs or cloud services, LeanKG is a single binary with auto-indexing, file watching, and 99% token savings that devs notice instantly in AI prompts. One-line installs configure MCP and agent instructions for your editor, plus plugins for OpenCode and Claude auto-inject graph context. It stands out for impact radius analysis and traceability from code to features/docs, solving real pains in large repos without vendor lock-in.

Who should use this?

Backend devs refactoring Rust/Go services who need quick "what breaks?" checks before changes. AI coding enthusiasts on Cursor/Claude tired of bloated prompts on mid-sized projects. Teams tracking business logic traceability in ai-assisted development without full RAG setups.

Verdict

Early alpha with 12 stars and 1.0% credibility—docs are solid but test coverage and multi-repo support lag. Worth a spin in a side project if you're deep into MCP/AI tools; skip for production until it matures.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.