Alternatives and similar repositories for OpenCUA

Users that are interested in OpenCUA are comparing it to the libraries listed below

• ByteDance-Seed / m3-agent
  ☆867Updated last week
• xlang-ai / aguvis
  [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
  ☆354Updated 6 months ago
• microsoft / GUI-Actor
  GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
  ☆331Updated last month
• Chengsong-Huang / R-Zero
  codes for R-Zero: Self-Evolving Reasoning LLM from Zero Data (https://www.arxiv.org/pdf/2508.05004)
  ☆601Updated this week
• CharlesQ9 / Alita
  ☆800Updated last week
• OS-Copilot / OS-Atlas
  OS-ATLAS: A Foundation Action Model For Generalist GUI Agents
  ☆376Updated 4 months ago
• ranpox / awesome-computer-use
  This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.
  ☆433Updated 3 months ago
• MiroMindAI / MiroFlow
  Build, manage, and scale your AI agents with ease.
  ☆451Updated last week
• BytedTsinghua-SIA / MemAgent
  A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
  ☆649Updated last month
• OSU-NLP-Group / UGround
  [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents
  ☆273Updated last month
• camel-ai / crab
  🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
  ☆369Updated 2 months ago
• modelscope / MCPBench
  The evaluation benchmark on MCP servers
  ☆198Updated last week
• inclusionAI / ASearcher
  ☆387Updated this week
• metauto-ai / agent-as-a-judge
  ⚖️ The First Coding Agent-as-a-Judge
  ☆619Updated 3 months ago
• OPPO-PersonalAI / Agent_Foundation_Models
  Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.
  ☆384Updated 2 weeks ago
• likaixin2000 / ScreenSpot-Pro-GUI-Grounding
  GUI Grounding for Professional High-Resolution Computer Use
  ☆251Updated last month
• ByteDance-Seed / Seed-Coder
  Seed-Coder is a family of lightweight open-source code LLMs comprising base, instruct and reasoning models, developed by ByteDance Seed.
  ☆549Updated 3 months ago
• microsoft / WindowsAgentArena
  Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
  ☆764Updated 4 months ago
• OPPO-PersonalAI / OAgents
  Implementation for OAgents: An Empirical Study of Building Effective Agents
  ☆251Updated 2 weeks ago
• sileix / chain-of-draft
  Code and data for the Chain-of-Draft (CoD) paper
  ☆325Updated 6 months ago
• qixucen / atom
  Atom of Thoughts for Markov LLM Test-Time Scaling
  ☆585Updated 2 months ago
• Leezekun / MassGen
  🚀 MassGen: An Open-source Multi-Agent Scaling System Inspired by Grok Heavy and Gemini Deep Think. Join the discord channel: https://dis…
  ☆419Updated this week
• InternLM / Intern-S1
  A Scientific Multimodal Foundation Model
  ☆561Updated last week
• Agent-on-the-Fly / Memento
  Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
  ☆1,230Updated this week
• Tencent / CognitiveKernel-Pro
  Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
  ☆333Updated 2 weeks ago
• camel-ai / loong
  🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.
  ☆409Updated last week
• ltzheng / agent-studio
  [ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents
  ☆218Updated 2 months ago
• DavidZWZ / Awesome-Deep-Research
  [Up-to-date] Awesome Agentic Deep Research Resources
  ☆437Updated 2 weeks ago
• SafeRL-Lab / agentic-web
  Agentic Web: Weaving the Next Web with AI Agents.
  ☆342Updated 2 weeks ago
• Dozi01 / MetaSPO
  ☆66Updated 3 months ago