DrissionPage MCP Server · Browser automation for Claude Code, Codex, and MCP clients

The AI toolkit for building reliable browser automations

An MCP server for parallel browser automation by AI agents with multiple cloud providers

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.

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

Browser automation MCP server for Claude, powered by Puppeteer.

Anti-detect browser automation CLI & Skills for AI agents — Camoufox-powered fingerprint spoofing, no bot-detectable Playwright leaks

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with agent-browser.

Stealth browser automation that actually works. Runs Camoufox (custom Firefox) in Docker with zero Chrome DevTools Protocol exposure, real OS-level mouse and keyboard input via PyAutoGUI, and a JSON HTTP API + MCP server to control it all remotely. Watch it live via noVNC.

Next.js Development for Coding Agent

General-purpose Playwright automation for coding agents

let any ai agent use the local browser

A browser runtime that lets AI agents control your real Chrome browser via MCP. Agents can explore websites, generate operation manuals, and reuse them to save tokens. AI操控你的真实浏览器。

Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off

Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.

One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local tools, and MCP.

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

Drive your real, logged-in Chrome from any AI agent (Claude Code, Codex, Cursor, VS Code) — works where headless dies. Reads emailed login codes from your Gmail, 40 tools, up to 20 concurrent sessions. MIT, local-only.

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.