#browser-automation

Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust

Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

OpenAI-compatible API proxy for ChatGPT web — expose ChatGPT as an MCP server, REST API, and OpenAI SDK endpoint via CDP-driven browser automation

Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runtime.

Give your DSH agent hands: drive a real browser (Edge/Chrome over CDP) from the chat — ref-driven clicking, per-session browsers, and a live cockpit panel. Zero runtime deps, no API key.

Chrome 浏览器扩展 + DeepSeek Harness 插件，让 AI Agent 直接操控你的真实浏览器。

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay, over the Chrome DevTools Protocol.

A minimal browser-agent harness - six tools, any model. pi for the browser.

CLI for browser automation: let any AI agent drive your real logged-in Chrome — you watch every action and can veto any tab. Zero deps, no relaunch, no MCP server. A11y snapshots + element refs, CDP screenshots, network capture

Skainet Bridge — local automation bridge for AI agents: one process, one port. MCP server + client, REST, browser extension, sandboxed exec. Independent project, unaffiliated.

Powerful local-first browser automation for AI agents with real Chromium, isolated profiles, MCP, Maqam approvals, and verifiable evidence.

OpenHuskyAgent

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Let Claude code, chatgpt codex or control your own Chrome. Chrome extension + MCP server: Jev, TypeSafe's decision model, picks each click in ~0.5 s for a fraction of a cent. MIT, bring your own OpenRouter key.

Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping

Charterion: Multi-Agent Engineering Control Plane for ChatGPT Web Agents - orchestration, task dispatch, browser control, durable state, worktrees, evidence, review, recovery, and self-hosting.

MCP server for adding inline, range-anchored comments to Google Docs — the one comment operation the Google Docs & Drive APIs can't do. For AI agents (Claude, Cursor, Copilot) that review documents.

NTXM Browser Mini is a lightweight, privacy-first desktop web browser designed from the ground up for developers, QA testers, and AI agents.

Trusty Squire signs up / in to websites for you so you don’t have to.

🌀 Wraith — the identity-borrowing stealth browser for autonomous agents (Camoufox stealth + WAAP clearing + MCP)

Claude Code can't always do browser tasks. Codex can. This skill hands the job to the Codex desktop app and reads the result back automatically, so you stop copy-pasting between two AIs.

Local Chrome runtime for AI agents: zero-focus background automation with deterministic R0-R4 risk firewall

Reusable Agent Skills (SKILL.md) for any AI agent — Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI and more

💖 Support Creator: https://pages.razorpay.com/pl_T1zknR655GpRoS/view — Turn a free NVIDIA NIM API key into a private, autonomous coding agent: plans, writes & runs code, and drives a real Chrome browser live in an on-screen Agent Computer. 100% local on macOS & Windows. One-command install. 💖 Please support the creator!

Control a real logged-in Chrome browser from AI agents on your VPS over a private Tailscale network. Includes both an API and an MCP server.

Query Gemini Notebook (formerly NotebookLM) directly from OpenAI Codex with local browser automation and source-grounded answers.

An AI agent in Chrome's side panel that reads and works on your tab. Bring your own key (Claude, OpenAI, Gemini, OpenRouter) or a local model (Ollama, LM Studio). No server, MIT.

Run local LLMs on Android to control real desktop browsers, with live chat relay between Chrome and Firefox.

Static analysis for AI automation workflows. Find prompt-injection paths, overpowered tools, and write-capable agent jobs before they run.

Token-cheap web browsing for AI agents (Claude Code, Codex, Cursor): search, navigate and an agent mode that closes cookie banners and acts human. CLI, no MCP, multi-browser (Chrome/Edge/Opera).

南方星火 SouthernSpark — Open-source AI agent skills & browser automation tools. Build, share & monetize practical AI workflows. 开源 AI Agent 技能包 & 浏览器自动化工具箱。

Give your MCP client (Claude Code, Codex) eyes and hands in your real, logged-in Chrome.

Agent search CLI: drives local headless browsers (Chrome/Firefox, self-built CDP/Marionette) to search the web with a stable JSON contract; native MCP tools (web_search / fetch_page)

👁️ /screenshot — real Chrome screenshots for your coding agent. A Claude Code plugin: 3 skills, a visual-reviewer agent and a bundled MCP camera.

🔭 Exploratory UI testing for AI coding agents, over MCP. Works with Claude Code, Cursor, VS Code, Codex, Gemini CLI and more: a structured view of a running web app, always-on oracles, a network-level write policy, cross-run memory and a gap-checked report.

Public showcase for Elyt, a private AI browser automation platform.

Free AI-agent risk self-check, security checklist, and USD 59 launch-readiness mini-audit offer.