Run AI in the browser

Easiest way to run AI models on your computer without installing any software. Chat with local small AI models directly in your browser. Your data never leaves your browser.

Overview

Run large language models like Llama 2, Mistral 7B, and Code Llama directly in your browser using WebLLM — no software to install, no API key, no cloud. The models download once and run entirely on your device using WebAssembly, so every message you type stays fully private. Your conversation history and folder organisation are saved locally in IndexedDB, persisting across sessions without any account or sync service involved.

Key Features

  • Tree-based folder organization for chats
  • Local LLM inference using WebLLM
  • Persistent chat history with IndexedDB
  • Resizable three-panel interface
  • Model selection and configuration
  • Real-time streaming responses
  • Complete client-side privacy
  • Search functionality across chats
  • Drag-and-drop folder organization
  • Message copying and timestamps

Common Use Cases

  • Private AI Assistant — Ask questions, brainstorm, or draft content using a capable local LLM without any of your prompts being logged by a cloud provider.
  • Offline AI Use — Download a model once, then chat with it on a plane, in a secure facility, or anywhere without internet access.
  • Code Help Without Leaks — Paste proprietary code into Code Llama 7B for suggestions and refactoring without it ever touching an external server.
  • Comparing Local Models — Switch between TinyLlama, Llama 2 7B, Llama 2 13B, and Mistral 7B side-by-side to judge quality versus memory trade-offs on your own hardware.
  • Research & Chat History — Organise long-running research threads into drag-and-drop folders with persistent, searchable chat history stored only in your browser.

How It Works
1

1. Choose an AI Model

Use the model selector at the top to pick from available local AI models. The model loads directly in your browser—no server or cloud required.

2

2. Organize and Start Chats

Create folders in the sidebar to organize your conversations. Start a new chat with the '+' button or select an existing one to continue.

3

3. Everything Stays Private

All chats, folders, and models run and are saved locally in your browser using IndexedDB. Your data never leaves your device.

Frequently Asked Questions

Does this tool require an internet connection?
No, after the initial model download, everything runs locally in your browser. You can chat with the AI completely offline.

Is my data or chat history sent to any server?
No. All chats, folders, and model data are stored in your browser using IndexedDB. Nothing is sent to any server or cloud.

How do I organize my chats?
You can create folders in the sidebar, drag and drop chats between folders, and rename or delete folders and chats as needed.

Can I use different AI models?
Yes. Use the model selector at the top to switch between supported models. Each model has different capabilities and memory requirements.

How do I stop a long or unwanted AI response?
While the AI is generating a response, click the stop button (red icon) next to the send button to halt generation immediately.

How is my chat history saved?
Your chat history and folder organization are saved automatically in your browser using IndexedDB. They will persist even if you close or refresh the page.

What browsers are supported?
Any modern browser with WebAssembly and IndexedDB support, such as Chrome, Edge, Firefox, or Safari. Sufficient RAM is required for larger models.

Can I copy messages?
Yes. Hover over any message and click the copy icon to copy its content to your clipboard.

What happens if I clear my browser data?
If you clear site data or IndexedDB storage, your chat history and folders will be permanently deleted.

Related Tools

Audio Transcriber Write — Private Grammar Fix & Translation Invoice Builder Markdown Editor & Live Preview Spreadsheet Converter Compress PDF