#computer-use Repositories
Discover 78 active open source GitHub repositories tagged with #computer-use, accumulating 559,410 total stars (averaging 7,171 stars per project). Leading this topic is browser-use/browser-use with 121,654 stars.
78 repositories total
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Local-first, cross-platform desktop workspace for Claude Code / AI Agents: multi-agent collaboration, Git worktrees, code diffs, a skills marketplace, multiple models, Computer Use, and desktop pets. Remote access via WeChat, Feishu, DingTalk, and H5. | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multiple models, Computer Use, task-aware desktop pets; remote access via WeChat, Feishu, DingTalk, Telegram, WhatsApp, and H5.
RobotGo, Go Native cross-platform RPA, GUI automation, Auto test and Computer use @vcaesar
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
๐ฅ Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
Open-source, self-hosted alternative to Grok Bot, Claude Duet, OpenAI Dots, Meta Muse, Instinct, Manus Cue: AI coworkers (named agents) with instructions, memory, routines, their own isolated computer, and your approval before they act.
Manina AI: Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, and any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.
๐ค Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT, Claude, Gemini, Grok, DeepSeek, Kimi, GLM and 70+ more through one Modelflare key. Reach them in the app, WeChat or Feishu; they remember you, work in the background, run commands and use your computer. Pay per use.
Run AI agents on real and isolated machines โ own kernel, filesystem, and network โ with <100ms boot. Local first, OCI compatible, pure Rust.
nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that gets things done, keeps working while the app is closed, remembers you, and asks before doing anything you can't undo. On Android, iPhone and iPad, Windows / macOS / Linux, and in the browser; your phone's screen and your computer are its hands.
๐พ Open Computer Use โ Open-Source Alternative to Codex Computer Use
Open-source personal agent with its own computer. It chases invoices, preps your calls, and cancels trials on real websitesโand asks before it acts. Runs on your machine with the model you choose. By n8n.
Roubao 2.0 for iPhone: an open-source iOS AI agent with owner-authorized Micro-X UI control, custom models, resumable tasks, and PDF reports. No Wi-Fi, jailbreak, computer, or extra hardware required at runtime (Mac + USB required for setup). Legacy Android version retained.
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills โ with sandbox isolation, multi-model support, and Feishu/Slack integration.
Personal AI agent harness for macOS, Windows, Linux, Android & iOS. New: Skales Scout, persistent AI agents that keep working on your desktop, each optionally in its own virtual machine. Chat, coding (Skales Code), Flow, automations, computer use, browser, voice, MCP, local LLMs (Ollama). BYOK, 26 providers. No Docker, no terminal.
Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.
Windows desktop automation for DeepSeek Harness: the in-box MCP client bridge mounted against CursorTouch/Windows-MCP, with an off-by-default Computer Use switch and an in-app dependency installer.
[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.
Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and browser, routines, memory and approvals. Web, desktop and phone apps. Docker Compose + Postgres. AGPL-3.0.
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.
Capri โ Free, open-source AI desktop pet, gaming overlay, and voice companion for Windows. A visual GUI for Claude Code, Ollama, DeepSeek, and MCP. Joins Discord calls, launches Steam games, comments on gameplay, and automates on-screen tasks offline.
Poki uses your iPhone like you do. An open-source agent app that runs on your iPhone, reads the screen, and taps, types and swipes in real apps with your own model account.
Full computer use for AI agents. Self-learning workflows. Native macOS. No screenshots required.
Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow + Littlebird alternative)
The Open-Source AI Agent OS inspired by OpenAI Dots, Meta Muse, OpenClaw, Hermes & Mem0. Autonomous 3-tier headhunting, Receipt & Verifier loops, scoped memory, and BYOM for Claude Code, Codex & Cursor.
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
Design a better vision toolkit and skills for text-only models to "see" images, supporting multi-image understanding, image Q&A, frontend UI restoration, GUI automation, etc., with optional seamless integration with multiple mainstream agents, and direct recognition of pasted images | A vision toolkit and skill designed for text-only LLMs โ 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
Automate with a computer-use agent (ComputerUse / CUA) for macOS, Windows, Linux, browsers, iOS, and Android. It sees the screen, clicks, types, browses, and writes code too. One agent, every computer.
Frequently Asked Questions
What is the most popular #computer-use repository on GitHub?
The top ranked open source #computer-use project on GitHub is browser-use/browser-use with 121,654 stars. Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
Which programming languages are most used in #computer-use repositories?
Among the top ranked #computer-use projects on GitHub, the most common programming languages are Python, TypeScript, Swift, Rust.
How is the #computer-use repository ranking calculated?
We track 78 active open source repositories tagged with #computer-use (500+ stars), totaling 559,410 stars with an average of 7,171 stars per repository. Rankings update daily from the GitHub API.