Explore / browser-use

browser-use

The standard library for letting AI agents drive a real browser — click, type, fill forms and complete tasks from a natural-language goal. 100k+ stars, Python.

105,001 11,561 Python MITupdated yesterday

agents web

View on GitHub Dispute this mapping →

Curator's take

When the task lives behind login walls, forms and JavaScript — 'book this', 'apply to that', 'put these in my cart' — this is the default tool: it feeds the agent a cleaned DOM, executes its clicks/typing, and recovers from the endless weirdness of real websites. Install-as-skill support means Claude Code/Cursor agents pick it up in one prompt. NOT for bulk data extraction — an LLM driving a browser is the slowest, most expensive way to scrape a thousand pages (use a crawler); and treat any agent-with-a-browser as having the keys to whatever it's logged into — sandbox accordingly.

Mapped by ShipWithAI editors · links verified

README.md

What can Browser Use do?

Browser Use lets an AI agent use a web browser the same way you do — it opens pages, clicks buttons, types, and fills in forms. You describe the task, and it completes it. For example, you can have it:

📋 Fill Forms

Task: "Fill in this job application with my resume and information."

Job Application Demo Example code ↗

🍎 Shop for Groceries

Task: "Put this list of items into my instacart."

https://github.com/user-attachments/assets/a6813fa7-4a7c-40a6-b4aa-382bf88b1850

Example code ↗

💻 Be Your Personal Assistant

Task: "Help me find parts for a custom PC."

https://github.com/user-attachments/assets/ac34f75c-057a-43ef-ad06-5b2c9d42bf06

Example code ↗

Quickstart

If you want to use Browser Use in your agent (Claude Code, Codex, Cursor, Hermes, OpenClaw, etc.), paste this prompt, and it sets everything up itself:

Install or upgrade browser-use to the latest stable version with uv using Python 3.12, run `browser-use skill install` to register the skill, and connect it to my browser. If setup or connection fails, follow https://gith

Continue your stack

What teams reach for next — and why each earns a place beside browser-use. Ranked by curator confidence.

Pairs well with

LangGraph

Build stateful, multi-actor LLM apps as graphs — durable execution, human-in-the-loop, streaming.

Why it fitsbrowser-use is the hands, LangGraph is the brain: wire it in as the browsing tool inside a stateful agent graph and keep planning, retries and human-in-the-loop where they belong.

CubeSandbox

Hardware-isolated microVM sandboxes for AI agents — sub-60ms boot, <5MB overhead, E2B-compatible API, self-hosted on your own KVM nodes.

Why it fitsAn agent driving a real browser is exactly the workload you want hardware-isolated: run browser-use sessions inside microVM sandboxes instead of on your own profile.

mails

Email infrastructure for AI agents — send, receive, search and auto-extract verification codes via CLI/SDK, backed by a Cloudflare Worker; free hosted @mails.dev mailboxes or self-host.

Why it fitsThe missing half of automated signup flows: browser-use drives the registration form; mails receives the verification email in the agent's own mailbox and hands back the code — no human inbox in the loop.

Alternative to See all + compare →

BrowserOS

Open-source agentic browsing, twice: BrowserClaw — a browser your MCP agent drives using your real logged-in sessions — and BrowserOS, a Chromium fork with a built-in AI agent.

Why it fitsSame job — giving an AI agent a real browser — from opposite ends: browser-use is the Python library you embed in your agent; BrowserClaw is a shipped browser your MCP client drives, riding your existing logins instead of fresh sessions.

page-agent

Alibaba's in-page GUI agent: one script tag gives any webpage its own AI agent — users drive the interface in natural language. TypeScript, tiny bundle, Chrome extension available.

Why it fitsSame end state — AI operating a web interface — from opposite sides of the fence: browser-use is the agent's browser for any site; page-agent is embedded by the site itself, giving its own users an agent.

stealth-browser-mcp

MCP server for undetectable browser automation: real Chrome via nodriver + CDP, Cloudflare/anti-bot bypass, AI-written network hooks — agents browse where Playwright gets blocked.

Why it fitsBoth hand an AI agent a real browser; browser-use optimizes for task completion on the open web, stealth-browser-mcp for surviving anti-bot walls — pick by whether detection is your bottleneck.