电脑 / 浏览器 Agent

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Secure and persistent computer for AI agents

An open-sourced end-to-end VLM-based GUI Agent

A JavaScript library for generating random user agents with data that's updated daily.

Automate with computer-use agent (ComputerUse / CUA) for macOS, Windows, Linux, Browser, iOS & Android. It sees the screen, clicks, types, browses and writes the code too. One agent, every computer.

Gemini Nexus 是一款面向浏览器场景的 AI 助手扩展，集成 Gemini Web、Gemini API 与 OpenAI 兼容接口，支持网页上下文、图像处理、工具调用和 MCP 浏览器控制。

WHartTest 是一款AI驱动的测试自动化平台，实现从需求到可执行测试用例的自动化生成与管理，帮助测试团队提升效率与覆盖率。 (WHartTest is an AI-driven test automation platform that automates the generation and management of executable test cases from requirements, helping testing teams improve efficiency and coverage.)

UI-Venus is a general-purpose foundation GUI agent for mobile apps, web platforms, and desktop operating systems using only screenshots as input.

Chrome sidebar extension that lets DeepSeek Harness operate your browser directly, no vision capabilities required. 一款 Chrome 侧边栏扩展程序，可让 DeepSeek Harness 直接操控您的浏览器，无需视觉能力。

The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.

Web-based browser profile manager for CloakBrowser — create, launch, and manage isolated browser profiles with unique fingerprints. Free, self-hosted Multilogin alternative

[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.

Playwright's API on a Rust CDP engine — Chromium browser automation for Python & Node, no driver subprocess. (Alpha)

🏝️ A CLI Tool to Automate Your Everyday Web Browser.

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

Web testing solution for non-developers on top of Puppeteer and Jest

Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.

Native Linux desktop control for AI agents (MCP, Pi, CLI): semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KDE, Hyprland, niri, COSMIC, i3, Sway, labwc and other wlroots compositors, and X11.

Browser-side WhatsApp Web automation library. Exposes the WPP JavaScript API for chats, messages, contacts, groups, media and events; powers WPPConnect integrations and extensions.

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

指纹浏览器（防关联浏览器 / 反检测浏览器 / Antidetect Browser）与住宅代理 IP 选型指南及开源资源汇总：整理 27 款主流指纹浏览器与 28 家代理 IP 的套餐价格，收录 Chromium 指纹定制、Camoufox、Patchright、反检测自动化与指纹检测工具。

Stack blocks visually to build complex browser workflows and execute them via API

Local-first open-source multi-profile fingerprint browser based on Chromium and Electron

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

Autonomous Android and computer use using any LLM (local or remote)

Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard

Open-Source fast local computer use

Terminal UI to get stuff done in the browser

Agent! now supports macOS 14.6 or later, Apple Silicon and Intel, latest release. The Best AI agent for Mac: drives any app via Accessibility, codes/builds in Xcode, automates AppleScript, JXA, Swift and SMAppService shell (user/root). 23 LLM providers, local/cloud, plus on-device Apple Intelligence and Jev guard. Auto-Pilot, MCP, Avatar.

使用 agent-browser-cli 进行浏览器感知与控制。适用于标签页扫描/切换、页面 JS 执行、Cookie、CDP、contentSettings、截图、文件上传、下拉框点击、tmwd_cdp_bridge 初始化和 Web 工具排障

DeepSeek Harness的Windows电脑操控插件 / Windows computer use for DeepSeek Harness

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

Your AI friend right in your browser

Local computer use on Apple silicon: on-device typed decisions with laya and form filling with CUA-S1-FORMS, driven through the macOS Accessibility API

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternative to ChatGPT Atlas, Perplexity Comet, Dia and Microsoft CoPilot Edge Browser

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).

响应快 省Token， Let AI agents (Claude Code, Codex, any MCP client) drive a real iPhone · 让 AI agent 操作真实 iPhone：读屏、点击、输入、滑动，USB 或 Wi-Fi，自有 XCTest runner，可回放的 App flow。Open source, self-hosted on macOS.

A powerful browser assistant for vibe surfing 一个开源的AI浏览器智能助手

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

The world’s #1 end-to-end job agent: semantic filters, ATS-optimized resumes, referrals from hiring managers — 100% hands-free.

DSH（DeepSeek Harness）插件：把 ego-lite 浏览器（给 AI Agent 用的 Chromium）接入 HARNESS——13 个结构化 ego_* 工具（文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离），内置 ego 运行时，Linux + Chrome 开箱即用，无需克隆官方仓库或手动构建。

Browser Use Box: a 24/7 Claude Code agent for Playwright-style browser automation with Browser Use Cloud, Telegram, and a real browser on any box you own.

Anti-detection browser server for AI agents — REST API wrapping Camoufox engine with OpenClaw plugin support

Agentic browser control driven by your own Claude / Cursor subscriptions

Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR) and acts by element name, with screenshots as the last resort. Multi-monitor aware, verifies every action, one safety gate.

Stop AI agents from doing things you didn't ask for.

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users install dsh-nuphus-mcp.