glincker

glincker / stacklit

Public

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Cursor, Aider.

12
1
100% credibility
Found Apr 11, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

Stacklit scans a codebase to generate a compact JSON index, visual maps, and diagrams that enable AI coding agents to quickly understand project structure, modules, dependencies, and conventions.

How It Works

1
🔍 Discover Stacklit

You hear about a simple tool that helps AI assistants instantly understand any codebase without wasting time reading every file.

2
💻 Run one command

In your project folder, you type a single easy command and it automatically scans all your code files.

3
See your project map appear

In seconds, helpful files pop up including a beautiful interactive visual map of your modules and connections that opens in your browser.

4
📁 Save the key files

You add the small summary file and diagram to your project so they're always ready for AI helpers.

5
🤖 Connect your AI assistant

With another quick command, it sets up your favorite AI coding tool to use the map automatically.

6
Keep it fresh
Auto-update

It adds a smart hook so the map stays current without you thinking about it.

🔧
Manual refresh

Run the command again whenever you want the latest view.

🎉 AI gets your code instantly

Now your AI assistant knows every part of your project in seconds, saving tons of time and thinking smarter.

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 stacklit?

Stacklit runs one command to scan your codebase and generate a compact JSON index that gives AI agents instant context – turning 50k+ tokens of file exploration into ~4k tokens of structured modules, dependencies, and exports. It also outputs a Mermaid graph for GitHub READMEs and an interactive HTML visualizer with graph/tree/table/flow views. Built in Go, it auto-configures Claude Code, Cursor, and Aider via MCP servers and git hooks.

Why is it gaining traction?

It beats Repomix and Aider maps by committing a tiny, parsable index to your repo instead of ephemeral dumps or huge prompts, plus visual diffs to check staleness. One-command setup injects 250-token nav maps into tool configs, detects monorepos (pnpm, Nx, Turbo), and hints test commands or feature locations. Framework detection across 11 languages via tree-sitter makes agents smarter without runtime overhead.

Who should use this?

AI-assisted devs on mid-to-large backends (FastAPI, Gin, Axum) where agents burn context navigating structure. Monorepo maintainers juggling apps/packages/services, or Cursor/Claude users seeking github one click context over manual prompts. Skip if your repo is tiny or you're not using AI coding tools.

Verdict

Promising for AI workflows despite 12 stars and 1.0% credibility score – thorough docs, examples, and CI/GitHub Action make it production-ready for early adopters. Run npx stacklit init today; regenerate costs milliseconds.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.