What it does
WebLLM runs language models inside a web browser, using your computer's graphics chip through a technology called WebGPU. Because nothing goes to a server, conversations stay on your device.
Developers can build it into websites using the same commands as OpenAI's service. You can try it at the WebLLM Chat demo site.
Who it's for
Web developers building private AI features, and anyone curious to try in-browser AI.
Can I use it without coding?
Developers only. A JavaScript library for developers. The demo chat site works in a modern browser. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Web browser
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Try the WebLLM Chat website to chat with an AI model running inside your browser.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- WebLLM: high-performance in-browser LLM inference engineHacker News · Sept 2026
- WebLLM: A High-Performance In-Browser LLM Inference EngineResearch paper · Dec 2024
- Web LLM – WebGPU Powered Inference of Large Language ModelsHacker News · Apr 2023