Explore Projects

Discover 15 open source projects

Active filters (1):
Search: computer-useร—
Clear all

Showing 1-15 of 15 projects

bytedance/UI-TARS-desktop

Multimodal AI agent stack for GUI and browser automation

28.6K
Stable
TypeScript
MCP Servers
Agents & Orchestration
TypeScript
#agent-tars#multimodal-ai#gui-agent

trycua/cua

Open-source infrastructure for AI agents that can control full desktops (macOS, Linux, Windows).

12.9K
Active
Python
Agents & Orchestration
Python
#agent#ai-agent#desktop-automation

web-infra-dev/midscene

A TypeScript-based UI automation tool for testing AI-powered web and mobile apps using vision-based models.

12.0K
Active
TypeScript
Computer Vision
React
#ai-testing#vision-based-testing#web-automation

go-vgo/robotgo

Go native cross-platform RPA, GUI automation, and computer use tools for AI-powered developers.

10.6K
Active
Go
Computer Vision
Go
#automation#rpa#gui

bytebot-ai/bytebot

Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands.

10.5K
Stable
TypeScript
AI Agents
TypeScript
#agent#automation#ai-tools

simular-ai/Agent-S

An open agentic framework that enables computers to act like humans

10.0K
Active
Python
React
#agent-computer-interface#in-context-reinforcement-learning#grounding

Upsonic/Upsonic

An agent framework for fintech and banks, with support for AI tools like OpenAI and LLMs.

7.8K
Active
Python
LLM Frameworks
API Clients & Testing
Python
#agent#fintech#banking

microsoft/fara

An efficient agentic model for computer use, focused on browser-based AI coding agents.

4.3K
Active
Python
Agents & Orchestration
AI Code Editors
Python
#agent#browser-use#computer-use

yuruotong1/autoMate

An AI-driven local automation assistant that uses natural language to make computers work by themselves.

3.8K
Experimental
Python
Agents & Orchestration
CLI Tools
Python
#agent#automation#rpa

A9T9/RPA

Open-source RPA software with computer vision, OCR, and integration with Anthropic's AI language model.

1.9K
Experimental
JavaScript
AI Coding Agents
MCP Frameworks
Selenium
#browser-automation#computer-vision#ocr

e2b-dev/open-computer-use

Open-source AI-powered computer use platform built with LLMs and a desktop sandbox

1.8K
Experimental
Python
LLM Frameworks
Agents & Orchestration
Python
#ai#llm#agent

showlab/ShowUI

Open-source end-to-end vision-language-action model for GUI agents and computer usage analysis.

1.7K
Active
Python
Agents & Orchestration
Component Libraries (React)
React
#agent#computer-use#gui-agent

trycua/acu

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

1.6K
Stable
Agents & Orchestration
LLM Frameworks
#ai#ai-research#computer-use

OpenAdaptAI/OpenAdapt

An open-source framework for AI-powered process automation with support for large language, action, and multimodal models.

1.5K
Active
Python
LLM Frameworks
Agents & Orchestration
Python
#ai-agents#process-automation#large-language-models

zai-org/CogAgent

An open-source end-to-end VLM-based GUI agent for developers building with AI tools.

1.1K
Experimental
Python
Agents & Orchestration
AI Code Editors
React
#agent#gui#vlm

Stay in the loop

Get weekly updates on trending AI coding tools and projects.