ATS-Dopi

LLMify

GitHubHTML
Sync GitHub: 9/15/2026

LLMify

100% Local No Build Required License MIT

Generate a structured llms.txt file for your project — without touching the terminal.

LLMify is a zero-setup, browser-based tool that lets anyone (even beginners) produce an llms.txt file for their codebase. Drag and drop a folder, and LLMify builds a clean, AI-ready description of your project in real time.

✨ Features

  • Drag & Drop a folder — drop a whole project directory onto the page, or click to browse. No CLI, no config.
  • Smart automatic filtering — heavy and irrelevant folders (node_modules, .git, dist, build, .venv, __pycache__, .next, coverage, …) and binary/image/archive files are silently excluded. Nothing to configure.
  • Simple toggle options
    • 🌳 Tree view — include a visual file tree of the project.
    • 📝 File summaries — add a short auto-generated summary for each file.
  • Live preview — the right pane shows the generated llms.txt in real time with lightweight syntax highlighting.
  • Quick actions
    • 📋 Copy to clipboard
    • ⬇️ Download llms.txt
  • Modern dark UI — glassmorphism, gradient accents, smooth animations, progress indicator while scanning.
  • 100% local — your files never leave your browser. No upload, no server, no tracking.

🚀 Quick start

LLMify is a single self-contained HTML file. No dependencies to install, no build step.

Option 1 — Just open the file

Download index.html and double-click it. It opens in your default browser. Done.

Option 2 — Serve it locally (recommended)

Serving over http:// enables the modern File System Access API in supported browsers.

# Python 3
python -m http.server 8765

# Node.js (npx)
npx serve

# PHP
php -S localhost:8765

Then visit http://localhost:8765 in your browser.

Option 3 — Host it statically

Drop index.html on any static host: GitHub Pages, Netlify, Vercel, Cloudflare Pages, S3, etc.

🧭 How to use

  1. Drop a folder onto the dashed zone (or click to pick one).
  2. Watch the progress indicator as LLMify scans your project.
  3. Toggle Tree view and File summaries on or off — the preview updates instantly.
  4. Click Copy to copy the result, or Download llms.txt to save it.
  5. Place the downloaded llms.txt at the root of your project.

That's it. AI assistants like ChatGPT, Claude, Cursor, and others can now read it to understand your project faster.

🤔 What is an llms.txt file?

An llms.txt file sits at the root of your project and describes its structure and content to AI models. It lets tools like ChatGPT, Claude, and Cursor quickly understand your codebase so they can better help you code, explain, or debug.

Learn more at llmstxt.org.

🧠 What gets filtered out

LLMify automatically ignores the noise so the output stays useful and compact.

CategoryExamples
Dependency dirsnode_modules, bower_components, vendor, jspm_packages
Build / cachedist, build, out, .next, .nuxt, .cache, .turbo, coverage
VCS.git, .svn, .hg
Python__pycache__, .pytest_cache, .mypy_cache, .tox, .venv, venv, env
IDE / editors.idea, .vscode
Lockfilespackage-lock.json, yarn.lock, pnpm-lock.yaml, composer.lock, Cargo.lock, poetry.lock
Secrets.env, .env.local, .env.production, …
Images.png, .jpg, .gif, .webp, .svg, .ico, .avif, …
Media.mp4, .mp3, .wav, .webm, .mov, …
Archives.zip, .tar, .gz, .rar, .7z, …
Binaries.exe, .dll, .so, .dylib, .wasm, .class, .jar, …
Fonts.ttf, .otf, .woff, .woff2, …
Databases.sqlite, .db, .mdb, …
Docs.pdf, .docx, .xlsx, .pptx, …
Minified / maps*.min.js, *.min.css, *.map

Only text and source-code files are read (JS, TS, Python, Go, Rust, Java, C/C++, HTML, CSS, Markdown, YAML, JSON, SQL, Dockerfiles, and many more). Each file is capped at 200 KB to keep things fast.

🌐 Browser support

FeatureChrome / EdgeFirefoxSafari
Click to select a folder (webkitdirectory)✅✅✅
Drag & drop a real folder✅✅✅
Modern File System Access API✅❌❌

Even without the File System Access API, the fallback (webkitdirectory + drag-and-drop entries) works in all modern browsers.

🛠️ Tech stack

  • HTML — single file, no framework required
  • Tailwind CSS (via CDN) — styling
  • Vanilla JavaScript — folder reading, filtering, generation, preview
  • File System Access API + webkitdirectory fallback — folder input
  • FileReader API — reading file contents locally

No dependencies. No build step. No backend.

📁 Project structure

LLMify/
├── index.html   # The entire application (HTML + CSS + JS)
└── README.md    # You are here

🤝 Contributing

Contributions are welcome! Feel free to open an issue or submit a pull request.

  1. Fork this repository
  2. Create your branch: git checkout -b feature/my-feature
  3. Commit your changes: git commit -m "Add my feature"
  4. Push to the branch: git push origin feature/my-feature
  5. Open a Pull Request

📄 License

MIT © LLMify

← Projets