Havuz

cc-haha, Claude Code ve diğer coding agent işlerini masaüstünde oturum, Git worktree, diff inceleme ve uzaktan erişim özellikleriyle yönetmeye yarayan bir çalışma alanıdır.

Neden yükseliyor · 180 günlük yaşında 14.727 yıldız ve son 28 günde 270 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor; ancak aynı dönemdeki 3 farklı yazar, bakımın sınırlı sayıda kişide yoğunlaşabileceğini gösteriyor. Yıldızlar gerçek kullanıcı sayısını kanıtlamaz.

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

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.

Open-source benchmark for browser AI agents on daily tasks.

Personal AI agent harness for macOS, Windows, Linux, Android & iOS. New: Skales Scout, lasting AI agents that keep working on your desk, eac

Native Linux desktop control for AI agents (MCP, Pi, CLI) — semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KD

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

Agent! now supports macOS 14.6 or later, Apple Silicon and Intel, latest release. The Best AI agent for Mac: drives any app via Accessibilit

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

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives t

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

Dodaios is an open-source agent OS for your desktop: it runs your coding agents, browser and apps by voice or chat, on your own machine. For

Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server fo

AI-first open source operating system for various devices, based on the Android.

The Grok Bot experience for your Hermes fleet: iMessage-style chat bubbles + a live window into your bots' computers. Not affiliated with xA

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

Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, leg

Open-source alternative to Claude Co-Work built by Claude. with BYOK

One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one r

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

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

Aetox harness: a local-first Windows AI environment - model, skills, team and memory as one system. Two doors - an Assistant that adapts to

A free, open-source AI agent that runs entirely on your machine — controls your computer like you would, works across any app, and handles a

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

Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, pic

Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — covering IM workspace integratio

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.

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

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

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,

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, sa

Drop-in OpenAI-compatible cache that replays repeated computer-use and agent workflows at near-zero cost.

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

Windows-first unofficial community desktop client for Grok Build CLI

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

🐧Operator-Use: AI that can do stuffs on your computer

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

One AI workspace for your models, agents, tools and computer.

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

A streaming action language for computer-use agents. LLMs emit one JSON action per line; the executor runs each the moment its newline arriv