Topic: "computer-use"
bytedance/UI-TARS-desktop
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
Language: TypeScript - Size: 44.9 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 13,432 - Forks: 1,088
web-infra-dev/midscene
Your AI Operator for Web, Android, Automation & Testing.
Language: TypeScript - Size: 341 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 8,788 - Forks: 523
Upsonic/Upsonic
The most reliable AI agent framework that supports MCP.
Language: Python - Size: 3.66 MB - Last synced at: 4 days ago - Pushed at: 14 days ago - Stars: 7,442 - Forks: 689
trycua/cua
c/ua is the Docker Container for Computer-Use AI Agents.
Language: Python - Size: 5.08 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 6,259 - Forks: 248
nanobrowser/nanobrowser
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
Language: TypeScript - Size: 711 KB - Last synced at: 6 days ago - Pushed at: 17 days ago - Stars: 5,522 - Forks: 463
simular-ai/Agent-S
Agent S: an open agentic framework that uses computers like a human
Language: Python - Size: 39.3 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 4,657 - Forks: 453
A9T9/RPA
Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.
Language: JavaScript - Size: 13.1 MB - Last synced at: 3 days ago - Pushed at: 20 days ago - Stars: 1,556 - Forks: 327
OpenAdaptAI/OpenAdapt
Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
Language: Python - Size: 28.9 MB - Last synced at: 26 days ago - Pushed at: 2 months ago - Stars: 1,243 - Forks: 175
trycua/acu
A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.
Size: 125 KB - Last synced at: 10 days ago - Pushed at: about 2 months ago - Stars: 1,217 - Forks: 81
showlab/ShowUI
[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
Language: Python - Size: 27.4 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1,064 - Forks: 64
e2b-dev/open-computer-use
AI computer use powered by open source LLMs and E2B Desktop Sandbox
Language: Python - Size: 1.48 MB - Last synced at: about 1 month ago - Pushed at: 2 months ago - Stars: 1,042 - Forks: 135
THUDM/CogAgent
An open-sourced end-to-end VLM-based GUI Agent
Language: Python - Size: 5.11 MB - Last synced at: 4 days ago - Pushed at: about 1 month ago - Stars: 941 - Forks: 74
microsoft/WindowsAgentArena
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Language: Python - Size: 191 MB - Last synced at: 4 days ago - Pushed at: 19 days ago - Stars: 699 - Forks: 68
bytebot-ai/bytebot
Bytebot is the container for desktop agents.
Language: TypeScript - Size: 30.2 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 621 - Forks: 39
BandarLabs/clickclickclick
A framework to enable autonomous android and computer use using any LLM (local or remote)
Language: Python - Size: 111 KB - Last synced at: 3 days ago - Pushed at: 3 months ago - Stars: 441 - Forks: 54
suitedaces/computer-agent
Desktop app powered by Claude’s computer use capability to control your computer
Language: Python - Size: 108 KB - Last synced at: 26 days ago - Pushed at: 4 months ago - Stars: 436 - Forks: 43
OS-Agent-Survey/OS-Agent-Survey
This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use".
Size: 11.4 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 271 - Forks: 12
inclusionAI/AWorld
Build, evaluate and run General Multi-Agent Assistance with ease
Language: Python - Size: 148 MB - Last synced at: about 16 hours ago - Pushed at: 2 days ago - Stars: 225 - Forks: 10
aditya-nadkarni/spongecake
Spongecake is the easiest way to launch computer use agents.
Language: JavaScript - Size: 27.7 MB - Last synced at: 23 days ago - Pushed at: 23 days ago - Stars: 128 - Forks: 16
Optexity/ComputerGYM
Foundation Model Training Using Human Demonstrations
Language: Python - Size: 291 KB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 104 - Forks: 4
chatsci/Aeiva
A general AI agent framework that can be adapted to various tasks and environments.
Language: Python - Size: 85.8 MB - Last synced at: about 1 month ago - Pushed at: 3 months ago - Stars: 100 - Forks: 16
bilalonur/awesome-llm-os
A curated list of awesome resources, tools, research papers, and projects related to the concept of Large Language Model Operating Systems (LLM-OS).
Size: 610 KB - Last synced at: 8 days ago - Pushed at: 14 days ago - Stars: 95 - Forks: 5
baryhuang/mcp-remote-macos-use
A zero-installation solution for AI agents to control remote macOS systems. Full desktop capabilities without extra software, using only built-in Screen Sharing. Works with Claude and any MCP client, offering native macOS experience with minimal setup and no additional API costs.
Language: Python - Size: 262 KB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 68 - Forks: 7
lvqq/intelli-browser
✨ Use natural language to control your browser, powered by LLM and playwright
Language: TypeScript - Size: 9.78 MB - Last synced at: 16 days ago - Pushed at: 6 months ago - Stars: 45 - Forks: 3
cyberdesk-hq/cyberdesk
Open source virtual desktops for AI agents
Language: JavaScript - Size: 19.1 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 43 - Forks: 10
reidbarber/webmarker
Mark web pages for use with vision-language models
Language: TypeScript - Size: 677 KB - Last synced at: about 11 hours ago - Pushed at: about 12 hours ago - Stars: 39 - Forks: 3
presidio-oss/factif-ai
AI-powered computer control for automated testing. Factifai uses vision models (Claude, GPT-4o, Gemini) to interact with applications naturally - clicking, typing, and verifying results just like a human would.
Language: TypeScript - Size: 108 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 27 - Forks: 23
SALT-NLP/PopupAttack
Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups
Language: Python - Size: 195 MB - Last synced at: 3 months ago - Pushed at: 5 months ago - Stars: 26 - Forks: 1
philfung/computer-use
try Computer Use on your Mac with a few clicks
Language: Python - Size: 105 KB - Last synced at: about 1 month ago - Pushed at: 6 months ago - Stars: 24 - Forks: 2
philfung/awesome-computer-use
Curated resources about automated GUI computer-use via LLMs. Highly opinionated, focus is on quality vs quantity.
Size: 24.4 KB - Last synced at: 14 days ago - Pushed at: 6 months ago - Stars: 22 - Forks: 2
pnmartinez/simple-computer-use
Open source implementation for computer use, using light OCR models and LLMs.
Language: Python - Size: 639 KB - Last synced at: about 5 hours ago - Pushed at: about 6 hours ago - Stars: 21 - Forks: 0
ArchiveBox/abx-spec-behaviors
🧩 Proposal to allow user scripts like "expand comments", "hide popups", "fill out this form", etc. to be reusable across pure browser environments, puppeteer, playwright, extensions, AI tools, and many other contexts with minimal adjustment.
Language: JavaScript - Size: 785 KB - Last synced at: 3 days ago - Pushed at: 2 months ago - Stars: 18 - Forks: 0
iris-networks/iris
This is the crud backend for our QA test application
Language: TypeScript - Size: 14.6 MB - Last synced at: 1 day ago - Pushed at: 3 months ago - Stars: 18 - Forks: 2
SawyerHood/computer-use-extension
This is OpenAI's computer use hooked up to a chrome extension.
Language: TypeScript - Size: 117 KB - Last synced at: about 1 month ago - Pushed at: 2 months ago - Stars: 15 - Forks: 1
webhiveos/WebHive
Meet WebHive, the AI-powered browser that takes care of tasks for you. No more endless clicks, tell it what you need, and it gets it done.
Language: Python - Size: 1.72 MB - Last synced at: about 1 month ago - Pushed at: 3 months ago - Stars: 11 - Forks: 0
nottelabs/open-operator-evals
Opensource benchmark evaluating web operators/agents performance
Language: Python - Size: 141 MB - Last synced at: 23 days ago - Pushed at: about 1 month ago - Stars: 10 - Forks: 0
Justmalhar/claude-ubuntu-os
Claude Computer Use API with Ubuntu that enables Claude to interact with and automate desktop environments. It allows seamless command execution through VNC or noVNC, enhancing productivity with secure, containerized workflows with Github Codespaces.
Language: Python - Size: 15.3 MB - Last synced at: about 1 month ago - Pushed at: 7 months ago - Stars: 10 - Forks: 1
ashbuilds/computer-use
Anthropic's Computer use implementation in Nodejs
Language: TypeScript - Size: 81.1 KB - Last synced at: 3 days ago - Pushed at: 7 months ago - Stars: 8 - Forks: 2
cloudycotton/browser-operator
Build your own AI operators like OpenAI
Language: TypeScript - Size: 33.2 KB - Last synced at: about 1 month ago - Pushed at: 4 months ago - Stars: 7 - Forks: 0
lx-0/computer-use-nodejs-demo
🤖 LLM-powered computer control through local and Docker environments. Features VNC integration, automated interactions, and a chat interface for natural language system control.
Language: TypeScript - Size: 1.16 MB - Last synced at: about 1 month ago - Pushed at: 6 months ago - Stars: 6 - Forks: 1
auto-browse/auto-browse-ts
Auto-Browse: AI Enabled Browser Automation
Language: TypeScript - Size: 750 KB - Last synced at: 12 days ago - Pushed at: about 1 month ago - Stars: 5 - Forks: 0
AB498/computer-control-mcp
MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.
Language: Python - Size: 5.11 MB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 4 - Forks: 0
nicholasoxford/computer-use-mac-demo
Anthropic's computer use controlling a Macbook
Language: Python - Size: 2.99 MB - Last synced at: 2 days ago - Pushed at: 7 months ago - Stars: 3 - Forks: 1
presidio-oss/factifai-agent-suite
AI-powered computer control for automated testing in your CI/CD pipelines. Factifai agent uses vision models (Claude, GPT-4o) to interact with applications naturally - clicking, typing, and verifying results just like a human would.
Language: TypeScript - Size: 2.08 MB - Last synced at: 6 days ago - Pushed at: 7 days ago - Stars: 1 - Forks: 0
Rajaniraiyn/ccu
Anthropic's Computer Use tools within VSCode
Language: TypeScript - Size: 55.7 KB - Last synced at: 3 days ago - Pushed at: 6 months ago - Stars: 1 - Forks: 0
qrexpy/OpenManus
Manus is incredible, but OpenManus can achieve any idea without an Invite Code 🛫!
Language: Python - Size: 3.26 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 0 - Forks: 0
alaa-nadi/UI-TARS-desktop
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
Language: TypeScript - Size: 37.6 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 0 - Forks: 0
aicompanionx/XBuddy-Desktop-Electron
A highly interesting cryptocurrency AI assistant
Language: TypeScript - Size: 247 MB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 0 - Forks: 0
someaka/wayland-mcp
MCP Server for Wayland
Language: Python - Size: 16 MB - Last synced at: 4 days ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0
Clad3815/open-computer-use
AI-powered assistant that controls a Windows environment through docker, allowing automated interaction with the desktop interface. Control your computer with natural language.
Language: JavaScript - Size: 110 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0
Mihonarium/food_ordering_agent
Use an LLM agent to automate ordering food and other items from Deliveroo, Uber Eats, DoorDash, etc.
Language: Python - Size: 31.3 KB - Last synced at: 5 days ago - Pushed at: 4 months ago - Stars: 0 - Forks: 1
mubashir1osmani/m4
build custom asics and fpga's using llms.
Language: Python - Size: 50.5 MB - Last synced at: 3 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0
