dive-browser

Dive is a native browser for macOS and Windows, built on the Chromium Embedded Framework, with a Rust core and a React chrome. It is keyboard-first, and its distinguishing feature is the set of tools beside the page: network, console, storage and accessibility panels, a device simulator, a screen studio, and an AI agent that can read and operate the tab. The agent lives in the side panel and can read the page, click, type, inspect requests and report back. Users can bring their own key for Anthropic, OpenAI, Google, OpenRouter, Groq, Mistral, DeepSeek or xAI, or run fully local with Ollama or LM Studio.

MCP is built in. Claude Code, Cursor and other Model Context Protocol clients can open tabs, read pages, click, type, take screenshots and tail the console and network over localhost, behind a bearer token. The developer dock includes network with request bodies, SSE and WebSocket frames and HAR export, console, storage, request mocking and rewriting, axe-core accessibility audits, Core Web Vitals, and an OpenAPI spec inferred from traffic. Full Chrome DevTools is one shortcut away.

Dive also provides workspaces and profiles with separate cookies, tabs and mock rules per project, switchable with a keystroke. DivePrivacy can run first-party ads and tracker lists in the request pipeline with per-site controls, off until turned on. DiveScreen records any tab as video or GIF, then allows cropping, zooming and cursor effects. Idle tabs unload after an hour away and keep their place. Sites can become apps when their manifest passes Chrome's install rules.