Havuz

Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Loc

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

lnwjud — local AI-agent runtime & MCP gateway

LCU, ChatGPT desktop app'in computer-use runtime'ını Codex dışındaki agent harness'lerinde kullanıma açan bir entegrasyon aracıdır.

Neden yükseliyor · Yeni bir projede 14 günde 546 yıldız ve 415 commit görülmesi, Codex computer-use yeteneğini başka harness'lere taşıma vaadinin dikkat çektiğini gösteriyor; ancak commit'lerin yalnızca 2 farklı yazardan gelmesi katkı tabanının dar olduğuna işaret ediyor.

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Browser automation and computer use for AI agents. One CLI and MCP server for your signed-in browser, native macOS apps, and real iPhones.

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 wi

open-computer-use, AI agent’ların MCP üzerinden macOS, Linux ve Windows masaüstü uygulamalarıyla etkileşmesini sağlayan bir Computer Use hizmetidir.

Neden yükseliyor · 163 günlük bir repoda 2.251 yıldızın yanında son 28 günde 22 commit ve 7 farklı yazar bulunması, ilginin güncel geliştirme faaliyetiyle de desteklendiğini gösteriyor. README’deki demo ve farklı agent entegrasyonları da ürünün nasıl kullanılacağını somutlaştırıyor; ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

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

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fres

Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protoco

Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmwar

Six-skill spec-driven engineering pod for Claude Code — scaffold specs, research, discover direction, generate design variants, implement, a

Evidence-backed visual regression audits for web apps with Playwright: responsive UI checks, accessibility signals, screenshots, measurement

Self-hosted message gateway for AI agents: Codex, QQ, WeChat/WeCom, Feishu, smart devices and desktop automation. | AI 消息网关：连接聊天、智能设备与 Agent

Teach AI how your work actually gets done. Capture real computer work, extract the workflow graph and judgment, then run it with Codex or yo

Local MCP server for stateful, fail-closed Logic Pro control and live project readback.

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ tools. Companion-first alternati

Control 1 or more machines using computer use tools that integrates with your agents

Open-source AI desktop assistant for Windows with computer use, browser automation, MCP tools, local memory, and scheduled tasks. Supports C

OSX launcher and GPU-accelerated CLI tool for AI agents. Open-source computer use tool.

Computer use CLI for AI agents

Cross-platform Computer Use plugin for DeepSeek Harness: observable desktop automation with an isolated virtual cursor, AX/UIA observation,

Myna Recorder — a Windows macro recorder you can read and edit. Image anchors, an auto clicker, an AI assistant that writes macros, Agent mo

Windows PowerShell toolkit for AI agents: Microsoft 365 (mail, calendar, Teams, SharePoint, OneDrive) via Work IQ + Microsoft Graph, Outlook

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server

Reasonix 跨平台桌面自动化插件（重构版）。精准层优先（UIA/AXAPI/AT-SPI2）+ 视觉层兜底（EasyOCR），归一化坐标协议；Windows / Linux (X11) / macOS 三平台均已实现（同一套公共代码），Wayland 与未授权场景自动降级视

Record desktop workflows once and compile them into reusable AI-agent skills for reliable replay.

A local-first Python personal AI assistant for reasoning, memory, voice, vision, automation, and device control.

Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop.

Text-first browser & background macOS control for DeepSeek Harness (DSH): target the right process and window without taking the user's poin

Graphical macro builder for Linux Mint. Chain steps: open apps, files, sites, commands; place windows; click; press keys; type text. Save th

Python desktop AI assistant for screen awareness, voice interaction, persistent memory, and computer automation

让 Agent 操控 Windows 桌面软件

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

Background computer use for desktop agents on Windows and macOS

CLI to inspect, screenshot, and control live Tauri development screens without running an MCP server.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST AP

A Python library for automating and controlling macOS.

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates),

Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own Ope

Open-source Computer Use MCP server for any coding agent — macOS, Windows, Linux. Accessibility-first, background input, agent pointer, zoom

Open-source local-first computer-use agent for Linux, Windows, and macOS, powered by local VLMs or compatible APIs.

Let agents work in your apps while you keep using your Mac.

Drive a GNOME Wayland desktop from AI agents. CLI-first, no portals, no consent dialogs.

Cross-platform Rust computer-use MCP server for macOS and Windows: AX/UIA, screenshots, OCR, pointer and keyboard input, clipboard, stdio, a

Open-source AI agent testing framework for browser and native desktop apps, with explicit tool effects, evidence, lifecycle, and trace contr

An MCP server that turns a Windows RAD Studio machine into a remote backend for coding agents: safe editing, real MSBuild builds, git, scaff

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread