Search Results - RepositoryStats

980

12.4k

apache-2.0

116

A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.

mcp vlm vite agent vision electron gui-agents mcp-server browser-use computer-use

Created 2025-01-19

287 commits to main branch, last one 18 hours ago

midscene web-infra-dev

474

8.1k

mit

53

Your AI Operator for Web, Android, Automation & Testing.

ai ai-test testing phone-use javascript browser-use computer-use gpt-operator

Created 2024-07-23

470 commits to main branch, last one 9 hours ago

Upsonic Upsonic

686

7.4k

mit

55

The most reliable AI agent framework that supports MCP.

mcp rag llms agent claude openai reliability computer-use agent-framework model-context-protocol

Created 2024-05-26

1,221 commits to master branch, last one 2 days ago

nanobrowser nanobrowser

430

5.3k

apache-2.0

28

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

ai agent manus openai ai-tools operator ai-agents web-agent automation javascript opensource browser-use multi-agent computer-use gpt-operator web-automation chrome-extension browser-extension

Created 2024-12-31

132 commits to master branch, last one 12 days ago

cua trycua

163

4.4k

mit

27

c/ua is the Docker Container for Computer-Use AI Agents.

cua lume agent apple macos manus swift ai-agent operator computer-use virtualization virtualization-framework

Created 2025-01-31

308 commits to main branch, last one 9 hours ago

Agent-S simular-ai

255

2.4k

apache-2.0

33

Agent S: an open agentic framework that uses computers like a human

mllm memory planning ai-agents grounding gui-agents computer-use computer-automation agent-computer-interface retrieval-augmented-generation in-context-reinforcement-learning

Created 2024-10-09

227 commits to main branch, last one 13 hours ago

RPA A9T9

320

1.5k

other

63

Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.

imacros anthropic computer-use selenium-ide web-scraping web-automation anthropic-claude browser-extension data-driven-tests browser-automation

Created 2017-08-04

97 commits to master branch, last one about a month ago

OpenAdapt OpenAdaptAI

175

1.2k

mit

13

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

Created 2023-04-12

939 commits to main branch, last one 2 months ago

ShowUI showlab

76

1.2k

apache-2.0

15

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

agent gui-agent computer-use vision-language-model vision-language-action

Created 2024-10-31

267 commits to main branch, last one about a month ago

acu trycua

77

1.2k

unknown

12

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

ai awesome computer ui-agent gui-agent ai-research computer-use

Created 2025-01-05

27 commits to main branch, last one 26 days ago

open-computer-use e2b-dev

139

1.1k

apache-2.0

12

AI computer use powered by open source LLMs and E2B Desktop Sandbox

ai llm agent claude anthropic computer-use

Created 2024-10-31

108 commits to master branch, last one about a month ago

CogAgent THUDM

72

915

apache-2.0

21

An open-sourced end-to-end VLM-based GUI Agent

glm vlm agent gui-agent computer-use

Created 2023-11-28

50 commits to main branch, last one 18 days ago

mac_computer_use deedy

132

790

unknown

13

A fork of Anthropic Computer Use that you can run on Mac computers to give Claude and other AI models autonomous access to your computer.

ai claude anthropic computer-use

Created 2024-10-24

19 commits to main branch, last one 5 months ago

WindowsAgentArena microsoft

66

667

mit

10

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

ai agentic windows ai-agent computer ai-research ai-benchmark computer-use desktop-agent

Created 2024-07-29

86 commits to main branch, last one 5 months ago

bytebot bytebot-ai

37

598

mit

4

Bytebot is the container for desktop agents.

cua llm agents docker gemini openai bytebot ai-tools ai-agents anthropic agentic-ai automation computer-use desktop-automation

Created 2025-02-03

115 commits to main branch, last one a day ago

computer-agent suitedaces

43

436

other

8

Desktop app powered by Claude’s computer use capability to control your computer

ai gui pyqt pyqt6 python ai-tools anthropic computer-use claude-3-5-sonnet

Created 2024-10-25

24 commits to main branch, last one 2 months ago

clickclickclick BandarLabs

51

430

mit

6

A framework to enable autonomous android and computer use using any LLM (local or remote)

molmo agents gemini ollama openai python operator antrophic framework computer-use generative-ai android-automation ai-agents-framework

Created 2024-12-16

44 commits to main branch, last one about a month ago

OS-Agent-Survey OS-Agent-Survey

12

253

unknown

5

This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use".

gui llms agent mllms survey operator os-agent gui-agent phone-use web-agent computer-use browser-agent computer-using os-agent-survey computing-devices computer-using-agent

Created 2024-12-12

199 commits to main branch, last one 12 days ago

AWorld inclusionAI

6

147

mit

10

Build, evaluate and run General Multi-Agent Assistance with ease

mcp phone-use agentic-ai mcp-server agent-swarm world-model computer-use gym-environment

Created 2025-03-14

421 commits to main branch, last one 2 days ago

spongecake aditya-nadkarni

16

125

mit

2

Spongecake is the easiest way to launch computer use agents.

llm docker openai python ai-agents automation computer-use ai-agents-framework

Created 2025-03-08

83 commits to main branch, last one a day ago

ComputerGYM Optexity

4

103

unknown

0

Foundation Model Training Using Human Demonstrations

llm browser-use computer-use foundation-models reinforcement-learning

Created 2025-02-20

96 commits to main branch, last one 6 days ago

Aeiva chatsci

16

100

apache-2.0

3

A general AI agent framework that can be adapted to various tasks and environments.

ai llm agent memory ai4science multimodal world-model computer-use computer-usage multi-agent-system large-languge-models self-evolving-systems

Created 2023-05-29

100 commits to main branch, last one 2 months ago

awesome-llm-os bilalonur

5

90

cc0-1.0

5

A curated list of awesome resources, tools, research papers, and projects related to the concept of Large Language Model Operating Systems (LLM-OS).

llm agent llmos llm-os awesome awesome-list computer-use operating-systems large-language-model large-language-models natural-language-processing

Created 2024-05-13

25 commits to main branch, last one 5 days ago

mcp-remote-macos-use baryhuang

6

57

mit

2

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, ...

macos-use mcp-server computer-use

Created 2025-03-21

48 commits to main branch, last one 7 days ago

intelli-browser lvqq

3

45

mit

1

✨ Use natural language to control your browser, powered by LLM and playwright

e2e claude anthropic e2e-tests playwright computer-use claude-3-5-sonnet

Created 2024-11-08

9 commits to main branch, last one 5 months ago

webmarker reidbarber

3

35

mit

2

Mark web pages for use with vision-language models

cua som llms gpt4o gpt4v claude gemini prompt qwen-vl operator playwright set-of-mark computer-use prompt-engineering computer-using-agent vision-language-model

Created 2024-04-29

90 commits to main branch, last one 23 days ago

PopupAttack SALT-NLP

1

29

unknown

1

Code repo for the paper: Attacking Vision-Language Computer Agents via Pop-ups

attack pop-up llm-agent computer-use claude-3-5-sonnet vision-language-model

Created 2024-11-04

7 commits to main branch, last one 4 months ago

computer-use philfung

2

25

unknown

1

try Computer Use on your Mac with a few clicks

llms macos claude anthropic computer-use large-language-models multimodal-large-language-models

Created 2024-10-31

33 commits to main branch, last one 4 months ago

WebHive webhiveos

0

11

mit

1

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.

gca gpt mcp llms agent chagpt claude gpt-4o openai assistant langchain chatgpt-app computer-use agent-framework chatgpt-operator model-context-protocol

Created 2025-01-29

297 commits to main branch, last one 2 months ago