AI-powered browser automation framework using CodeAgent and CDP for autonomous web interaction.
openbrowser-ai is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view billy-enrizky/openbrowser-ai --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
OpenBrowser lets you automate web browsers using AI. Instead of writing complex scripts, you tell the AI what to do, and it writes and runs the code for you. It can fill forms, scrape data, book flights, and more, all autonomously.
OpenBrowser is a framework for intelligent browser automation. It combines direct Chrome DevTools Protocol (CDP) communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously. Key features include: CodeAgent architecture for dynamic code generation, raw CDP communication for speed and control, vision support via screenshot analysis, support for 15+ LLM providers (OpenAI, Anthropic, Google, etc.), MCP server for integration with Claude Desktop and other AI assistants, CLI daemon with persistent browser sessions, workflow recording and replay, video recording, and a cloud platform with real-time VNC streaming, saved logins, and scheduled workflows. It is designed for developers building AI agents, automation engineers, and anyone needing reliable browser automation.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 4 days ago.
233 GitHub stars indicate community interest.
1 open issues signal maintenance load.
MIT license detected.
Automate form filling and data entry on web applications
Scrape product data from e-commerce sites like Walmart
Book flights or make reservations automatically
Record and replay browser workflows for testing or monitoring
Integrate with AI assistants via MCP for autonomous web tasks
Automated browser actions may violate website terms of service; use responsibly.
Storing credentials or cookies in cloud platform requires trust in provider's security (KMS encryption used).
Running arbitrary LLM-generated code could pose security risks; review generated code before execution.
233
Stars
19
Forks
1
Issues
MIT
License
Extract any website's complete design system with one command.
Generate design system documentation for UI components directly from your AI agent, rendering into Figma or portable .md files.
Argos is an open source visual testing platform that detects unintended UI changes to help teams maintain quality.
3 security/trust notes recorded.
Setup difficulty is 3/5.