billy-enrizky/openbrowser-ai
OpenBrowser is a framework for intelligent browser automation. It combines direct 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.
Supports 12+ LLM providers (OpenAI, Anthropic, Google, Groq, AWS Bedrock, Azure OpenAI, Ollama, DeepSeek, and more) with vision-based screenshot analysis and video recording capabilities. Features a persistent Jupyter-like execution namespace where generated Python code can reference previous browser state, and provides MCP (Model Context Protocol) integration for Claude Desktop alongside a CLI daemon mode for direct bash execution via the `-c` flag.
180 stars.
Stars
180
Forks
13
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/billy-enrizky/openbrowser-ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
alibaba/page-agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
4ier/neo
Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas,...
CloakHQ/CloakBrowser
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with...
hanzili/hanzi-browse
let any ai agent use the local browser
nicobailon/surf-cli
The CLI for AI agents to control Chrome. Zero config, agent-agnostic, battle-tested.