Cluster 436861

11 repos

Python · 5

Rust · 2

HTML · 1

TypeScript · 1

agent ·70,867

computer-use ·70,514

browser-use ·55,177

vlm ·41,695

gui-agent ·41,308

mcp ·39,423

multimodal ·38,998

agent-tars ·38,916

gui-operator ·38,916

cowork ·38,916

Related clusters

Cross-platform terminal and CLI tools24 Cluster 46214523 Cluster 46214140 Cluster 46221922 Cluster 46213238 Cluster 46212432

THUDM/CogAgent

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

Python

1,196

50 commits

zai-org/CogAgent

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

Python

1,196

50 commits

microsoft/fara

Fara1.5 – A family of frontier computer use agent models

Python

6,175

51 commits

microsoft/Fara1.5-9B

Model

No description

4 commits

microsoft/Fara1.5-4B

Model

No description

3 commits

bytedance/UI-TARS-desktop

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

TypeScript

38,916

1,109 commits

runamu/monday

[CVPR 2025] Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents

Python

3 commits

trycua/cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training,…

HTML

22,408

4,085 commits

avifenesh/computer-use-linux

Linux desktop control over MCP — AT-SPI, GNOME Shell, Wayland portals, ydotool

Rust

507

101 commits

microsoft/magentic-ui

MagenticLite is an experimental agent that works across the browser and local file system

Python

10,086

820 commits

syswonder/robonix

The Agentic Operating System for Robots

Rust

353

1,379 commits