Search

More Filters

Show More
Add Listing
Go Back

browser use

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

browser-use is a Python library and agent framework designed to let AI models control a web browser to automate real web tasks. The repository provides an Agent abstraction, LLM adapters (examples include ChatOpenAI), and orchestration components so developers can describe tasks and run them against Chromium via Playwright. It is aimed at building browser-capable agents that can navigate pages, extract DOM information, fill forms, open tabs, and perform multi-step workflows. The README includes quick start instructions for pip installation and Playwright setup, environment variable names for multiple model providers, and demonstrates end-to-end use cases such as shopping automation, applying to jobs, transferring LinkedIn leads to Salesforce, writing in Google Docs, and scraping Hugging Face model listings. The project also offers a CLI, Web UI and Desktop App integrations, a hosted cloud option, example scripts, and documentation for extending capabilities with MCP servers.

Links

Stars
67636
App URL
https://github.com/browser-use/browser-use
Github Repository
https://github.com/browser-use/browser-use/blob/main/README.md

Categorization

App Details

Features
The project exposes an Agent API and controller primitives for composing browser automation tasks and integrates Playwright-backed Chromium execution. It supports multiple LLM providers via environment-configured keys and includes an example LLM adapter (ChatOpenAI). MCP (Model Context Protocol) support is built in so browser-use can act as an MCP server and connect to external MCP servers using MCPClient to register additional tools. Distribution includes a CLI package, examples folder with many use-case scripts, demos, and templates for common tasks. There are provisions for testing agent tasks in CI by adding YAML task files, a roadmap covering DOM extraction, memory and planning improvements, workflow recording/rerun ambitions, and considerations for parallelizing subtasks to scale large jobs.
Use Cases
browser-use helps developers and teams rapidly prototype and deploy AI-driven browser automation by handling browser control, LLM integration, and tool registration. It reduces the boilerplate needed to build agents that scrape sites, fill forms, manage multi-tab workflows, and interact with web applications like Google Docs or Salesforce. MCP compatibility makes it straightforward to extend an agent with external tool servers or to surface browser tools to MCP clients. The CLI, Web UI, desktop app, and a hosted cloud option let users test and run agents in different environments. Built-in examples, CI task testing, and documentation lower friction for validation and contribute toward more robust, testable automation agents.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*