browser-use
View on GitHubAgents that use the browser.
Browser Use is a Python library that lets LLM agents drive a real browser via Playwright to complete multi-step web tasks such as booking, form filling, and scraping. Supports OpenAI, Anthropic, Gemini, Groq, and local Ollama models, with custom tools, CLI/skill integration, and optional cloud browsers.
Use Cases
Automating multi-step web tasks like booking appointmentsFilling and submitting web forms with LLM controlWeb scraping and structured data extractionReusing logged-in Chrome profiles for authenticated browsingHandling CAPTCHAs and dynamic pages in agent workflowsGiving CLI coding agents (Claude Code, Codex) browser accessRunning browser agents locally with open-source models via OllamaQA/regression testing of web UIs with natural-language tasks
Built With
- Language
- Python
- Frameworks
- Playwright · Pydantic · MCP · aiohttp · anyio · cdp-use · Ollama · OpenAI SDK · Anthropic SDK · Google GenAI SDK · Groq · Click · Rich · InquirerPy · uv · Docker
Tags
browser-automation · ai-agents · computer-use · playwright · web-scraping · llm · python · browser-agent · task-automation · autonomous-agents · cli · mcp · structured-output · captcha-solving · multi-model · headless-browser