Computer use
agents that operate a desktop or GUI
feder-cr/invisible_dots feder-cr/invisible_dots is clearly the leader by adoption and scope; before choosing, decide whether you need a high‑capability, VM/browser‑backed autonomous agent (what the leader provides) or a specialized tradeoff — privacy, OS/device integration, replayable determinism, auditability, or developer ergonomics. Those practical tradeoffs, not star count, should drive your selection.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 15.1k +98/7d | CLIWeb app | AnthropicOpenAIBYOKOllama / local | Diff + Worktree | Approval gating | ●●●●● | Self-hostable | ●●●●● | Requires configuring your model provider API key (third‑party billing applies) |
⭐ 14.3k +22/7d | CLIWeb app | BYOKGemini | Whole-repo analysis | Human-in-the-loop | ●●●●● | Cloud API key | ●●●●● | Your LLM API key; provider charges apply |
⭐ 13.1k +1658/7d | CLIIDECoding-agent pluginWeb appCI | OpenAIAnthropicGeminiFixed provider | Diff + related files | Pre-exec Safety Net | ●●●●● | Self-hostable | ●●●●● | Self-hosted runtime; model usage may incur cloud API costs |
⭐ 12.7k +61/7d | CLIWeb app | BYOKOpenAIAnthropicGeminiFixed provider | Single-screen context | Basic filters | ●●●●● | Cloud APIs (your key) | ●●●●● | Your API keys (provider-dependent) |
⭐ 10.1k +594/7d | Web app | BYOK | Document-level | Snapshots & diffs | ●●●●● | Self-hostable (BYOK) | ●●●●● | Free app; uses Genspark proxy by default or your API key for model costs. |
⭐ 6.7k +273/7d | Web appCLICI | BYOKOpenAIAnthropicGemini | Workspace access | Policy and audit | ●●●●● | Cloud APIs w/ key | ●●●●● | Requires CopilotKit license and your model API key. |
⭐ 2.6k +163/7d | CLICoding-agent plugin | Fixed provider | Local UI only | None mentioned | ●●●●● | Fully local | ●●●●● | Free, local |
⭐ 32.2k +174/7d | CLIWeb app | Fixed provider | Local files only | Permission gating | ●●●●● | Self-hosted + cloud | ●●●●● | Requires OpenRouter API key |
⭐ 4.3k +28/7d | CLI | Fixed provider | Recording only | Manual review/edit | ●●●●● | Copilot cloud required | ●●●●● | Requires GitHub Copilot access |
⭐ 2.2k +10/7d | Web appCLI | BYOKOpenAIAnthropicGemini | Diff + related files | None mentioned | ●●●●● | Self-hostable | ●●●●● | Use your API key or third‑party relays for external models; desktop app is local-first |
⭐ 2.2k +13/7d | CLI | BYOKOpenAIAnthropicGemini | Workspace-wide | Basic filters/config | ●●●●● | Local app + API keys | ●●●●● | You provide an API key; model provider billing applies. |
⭐ 1.9k +20/7d | CLICoding-agent plugin | OpenAIAnthropicFixed provider | Diff only | Permission gating | ●●●●● | Self-hostable | ●●●●● | Free desktop app; external API costs may apply. |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
A desktop-first, local-first Claude Code workstation that combines worktree-aware code diffs, Computer Use desktop control, H5 remote access and IM integrations in one app.
Self-evolving agent that crystallizes each solved task into a persistent, reusable personal skill tree from a minimal (~3K-line) seed.
Provides a native MCP server that lets AI IDE assistants drive real Android devices with multimodal targeting, safety nets, and replayable diagnostics.
An open-source, research-backed GUI agent framework that combines grounding models and optional local code execution and achieves SOTA (surpassing human performance on OSWorld).
A full open-source, desktop Office suite that embeds document-aware AI agents and byte-preserving .docx editing with fully local PDF→Word/PowerPoint/Excel conversion.
Runs each agent in an isolated, browser-backed per-agent 'computer' with a central gateway that enforces CEL policies and records an auditable trail of every action.
Open-source, self-hosted MCP implementation of Computer Use that provides a local alternative to Codex Computer Use and integrates with multiple agent clients.
Provides self-hosted autonomous desktop agents that run in hardware-accelerated, persistent VMs with a patched stealth browser to avoid anti-bot detection.
All repositories (38)
Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H…
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token co…
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflow…
Agent S: an open agentic framework that uses computers like a human
Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI age…
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate s…
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action…
Desktop app that records your on-screen work session and uses the GitHub Copilot SDK to reconstruct it as an i…
👾 Open Computer Use – Open-Source Alternative to Codex Computer Use
A fully functional AI Agent desktop client that supports Webui access and can be creatively customized and exp…
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — w…
A native, all-in-one workspace for databases, SSH, SFTP, terminals, remote desktop, monitoring, and AI.
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps th…
For EHRs, payer portals, and any app your team clicks through. A person or an agent shows the task; OpenAdapt…
Install one APK and it operates any app on your phone — reads the screen, taps buttons, types. No integrations…
Give your AI agent eyes and hands on iOS Simulator and Android emulator/devices.
The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fu…
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
PiDeck 是一个开源的桌面工作台，用于在本地项目目录中统一管理 PI | DSH Agent 会话，并支持导入 Codex、Claude 本地会话以便统一浏览和恢复。支持多项目工作区、会话历史、Git 集成、内置终端…
Open source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then…
Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment set…
嘉立创EDA专业版(EasyEDA Pro)自动化：给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作，CLI / Agent Skill / stdio MCP 三形态融合接入。承接…
One chat. Every agent. A universal interface for AI agents running on your computer.
Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that op…
DeepSeek Harness (DSH) plugin: a live iOS Simulator — and a USB-connected iPhone — inside the conversation. 22…
Pi Desktop: a free, open source desktop GUI for the Pi coding agent and oh-my-pi. Chat, edit files, run a term…
Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and…
DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream insid…
A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local…
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher…
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
The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click…
Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with st…
Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and…
A menu-bar macOS agent loop: every N minutes it asks Claude/Codex what's overloading your Mac and suggests one…
Hosted alternatives
If running your own reviewer is more ops than you want, these managed services cover the same job.
Anthropic's hosted computer-use capability: Claude drives a virtual desktop through the API, so you get screen-grounded control without building the perceive-act loop or running a VM.
Try Claude Computer Use →A managed agent that operates a browser and desktop tasks on OpenAI's infrastructure, the hosted counterpart to running a local computer-use harness yourself.
Try OpenAI Operator →Rents ready-made cloud desktops and browsers for agents to control, so you point an existing agent at a managed machine instead of provisioning and securing one.
Try Scrapybara →