#computer-use (30 Repositories)
Ranked open-source repositories tagged with #computer-use, scored by pull request acceptance likelihood and maintainer engagement velocity.
72.6%
24.9h
30 repositories tagged #computer-use
razzant/ouroboros
Ouroboros — self-creating AI agent. Born Feb 16, 2026.
arcboxlabs/arcbox
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
ThinkFlowLab/system1-agents
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
agent-sh/computer-use-linux
Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool
CelestoAI/SmolVM
Open-source AI sandbox infrastructure with unified API for VMMs -- Firecracker, QEMU and libkrun.
OrgoAI/bops
Bops: a team of AI bots that run your business ops, each with its own computer, email and phone number. bops.bot
milind-soni/OpenMausBot
Open-source Grok Bot alternative with a virtual machine that bots can use
cuga-project/cuga-agent
CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features.
NanmiCoder/cc-haha
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 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5.
feder-cr/Jobs_Applier_AI_Agent_AIHawk
Open source AI job application bot in Python: browser automation and web scraping to read job postings, then auto-apply with a tailored resume and cover letter for each posting.
web-infra-dev/midscene
See interfaces like a human. E2E testing in natural language.
TIGER-AI-Lab/ClawBench
Open-source benchmark for browser AI agents on daily tasks.
trycua/cua
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
boringcomputers/nehemiah
On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.
CursorTouch/MacOS-MCP
Lightweight MCP server for computer use in MacOS
secondly-com/OpenPhone
AI-first open source operating system for various devices, based on the Android.
OpenAdaptAI/OpenAdapt
Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.
milind-soni/tiptour-macos
Open-Source fast local computer use
NakaokaRei/SwiftAutoGUI
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
iFurySt/open-codex-computer-use
👾 Open Computer Use – Open-Source Alternative to Codex Computer Use
YV17labs/GhostDesk
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, legacy software, internal tools. No API needed. One Docker command.
useagenthq/useagent
The open-source Devin alternative. Run Claude Code, Codex, OpenCode or Pi in isolated cloud workspaces you can self-host.
agent-sandbox/agent-sandbox
Agent-Sandbox is an easy-to-use, enterprise-grade sandbox platform for AI Agents — letting them securely run untrusted LLM-generated code, Browser use, Computer use, and deploy websites, among other tasks.
CelestoAI/celesto
Secure and persistent computer for AI agents
mrpulor-gh/nuphus-mcp
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.
Anionex/codex-vision-proxy
让纯文本模型在 Codex 中无障碍看图(view_image)的更优方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ A superior approach for enabling text-only models to seamlessly use Codex’s built-in view_image, plus a vision toolkit & skill designed for pure-text LLMs.
Anionex/codex-deepseek-vision
让纯文本模型在 Codex 中无障碍调用内置看图工具（view_image）的方案，附为纯文本 LLM 设计的视觉工具包 ｜ Let text-only models call Codex's built-in view_image seamlessly, plus a vision toolkit designed for text-only LLMs.
drewnekota/cetus
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.
OmniJev/OneJev
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.
nano-muse/nanoMuse
nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.