Awesome-Gui-Agents

KO | EN

gitlite — search

#typescript #ai-agents #ai #dsh-plugin #deepseek-harness #open-source #claude-code #codex #cli #developer-tools #react #windows

Awesome-Gui-Agents

★ 69 Open GitHub ↗

Awesome list of GUI agents (browser and computer use)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Awesome GUI Compute Agents

A curated list of GUI (Graphical User Interface) compute agents - AI systems that can see, understand, and interact with graphical interfaces like humans do.

This project is maintained by [Parni](https://x.com/ParnianBrk) and [Ian](https://x.com/ian_derrington). Follow [Supernal Intelligence](https://x.com/supernalasi) for more updates.

**Website**: [supernalintelligence.com](https://www.supernalintelligence.com/)  
**Join our Discord**: [Supernal Intelligence Discord](https://discord.gg/J9pU82wP)

For more complete data and the latest information, please visit our website: [supernalintelligence.com](https://www.supernalintelligence.com/)

## What are GUI Compute Agents?

GUI compute agents are AI systems designed to interact with graphical user interfaces just like humans do. They can:
- See and understand screen elements
- Click buttons, type text, and drag elements
- Navigate through applications and websites
- Complete complex visual workflows
- Automate GUI-based tasks through natural language instructions

## Contents

- [Commercial Agents](#commercial-agents)
- [Open Source Agents](#open-source-agents)
- [Research Projects](#research-projects)
- [By Environment](#by-environment)
  - [Browser-Based Agents](#browser-based-agents)
  - [Desktop Agents](#desktop-agents)
  - [Physical World Agents](#physical-world-agents)
  - [Cloud Agents](#cloud-agents)
  - [Multi-Device Agents](#multi-device-agents)
- [By Task Complexity](#by-task-complexity)
- [Resources](#resources)

## Commercial Agents

| Name | Developer | Status | Key Features | Environment |
|------|-----------|--------|-------------|-------------|
| [Ace](https://generalagents.com/ace/) | General Agents | Upcoming (2025) | Achieved 20× human speed on UI tasks; controls full computer via screen pixels | Desktop, Browser |
| [ACT-1](https://www.adept.ai/blog/act-1) | Adept AI | Released (2022) | Pioneer in digital actions; self-correcting behavior | Desktop, Browser |
| [CloudCruise](https://www.cloudcruise.com/) | CloudCruise | Released | Cloud-based GUI automation; enterprise-grade | Cloud, Browser |
| [Felluo AI](https://felluo.ai) | Felluo | Released | Vision-based GUI automation; supports both browser and desktop interactions | Desktop, Browser |
| [Adaptive.AI](https://adaptive.ai/) | Adaptive AI Inc | Released | AI risk management framework; technology strategy consulting | Browser |
| [AgentGPT](https://github.com/reworkd/AgentGPT) | Reworkd | Released (2023) | User-friendly interface for creating goal-oriented agents | Browser |
| [AI Agent Studio](https://www.automationanywhere.com/products/process-discovery) | Automation Anywhere | Released (2025) | Handles structured and unstructured data; creates AI agents for enterprise automation | Browser |
| [Apple Intelligence Agents](https://www.apple.com/apple-intelligence/) | Apple | Upcoming (2025) | Deep OS integration; privacy-focused | Phone, Desktop |
| [AskUI Vision Agent](https://www.askui.com/) | AskUI | Released | Cross-platform functionality without virtual machines | Desktop, Browser, Phone |
| [Beam AI](https://www.beam.cloud/) | Beam | Released | Agentic Process Automation platform for customer support, onboarding, sales proposal generation | Browser |
| [Claude Agent Kit](https://www.anthropic.com/solutions/agents) | Anthropic | Upcoming (2024) | Official toolkit for building Claude-powered agents | Browser |
| [Claude Computer Use](https://www.anthropic.com/news/claude-computer-use) | Anthropic | Released (2024) | Works on desktop apps and browsers; AI model-based approach | Browser, Desktop, Multi-device |
| [Devin](https://cognition.dev) | Cognition Labs | Upcoming (2025) | Full-stack programming capabilities with browser access | Desktop, Browser |
| [Fuyu-Heavy](https://www.adept.ai/blog/adept-fuyu-heavy) | Adept AI | Released (2024) | Ranked 3rd best vision-action model behind GPT-4V and Gemini Ultra | Desktop, Browser |
| [Gemini 1.5 Pro (Tool Use)](https://ai.google.dev/gemini-api) | Google | Released | Long context, tool orchestration in Workspace | Browser |
| [Google Mariner](https://deepmind.google/discover/blog/introducing-mariner-ai/) | Google DeepMind | Unreleased | High WebVoyager benchmark performance | Browser |
| [Gumloop](https://www.gumloop.com/) | Gumloop | Released (2023) | Visual workflow canvas; 90+ pre-built templates; Chrome extension for web automation | Browser |
| [Highlight AI](https://highlight.run/) | Embedded Intelligence | Released (2024) | Instant Q&A and automation on desktop; strong privacy focus | Desktop, Browser |
| [Hyperbrowser](https://www.hyperbrowser.ai/) | Hyperbrowser.ai (YC Backed) | Released (2024) | Sub-second browser launch, 10,000+ concurrent browsers, CAPTCHA solving | Browser |
| [Lindy](https://lindy.ai) | Lindy.ai | Released | Virtual AI assistant for daily business tasks | Browser |
| [Manus](https://monica.im/) | Monica AI (China) | Released (2024) | World's first general AI agent; SOTA on GAIA benchmark | Desktop, Browser, Phone |
| [MultiOn (now Please AI)](https://please.com/) | Please AI | Released (2023) | Multi-step web tasks end-to-end; preference learning | Browser |
| [OpenAI CUA (Operator)](https://openai.com/index/cua-preview/) | OpenAI | Released (2025) | High benchmark performance; uses reasoning models tech | Browser, Desktop |
| [Perplexity Comet](https://www.perplexity.ai/comet) | Perplexity AI | Upcoming (2025) | Autonomous multi-step search with citations | Browser |
| [Project Jarvis](https://ai.google/discover/jarvis/) | Google | Rumored | Computer-using agent system; few details available | Desktop, Browser |
| [Proxy](https://www.proxyagent.ai/) | Convergence AI | Released (2025) | Handles concurrent sub-tasks; cheaper alternative to Operator | Browser |
| [Relay](https://relay.club/) | Relay.app | Released (2021) | Clean, simple interface; extensive app integrations | Browser |
| [Relevance AI](https://relevance.ai/) | Relevance AI | Released | Drag-and-drop skill building, templates, integrations | Browser |
| [ServiceNow AI Agents](https://www.servicenow.com/products/now-platform-ai.html) | ServiceNow | Released | Built-in governance, analytics, text-to-action capabilities | Browser |
| [Vy](https://vercept.com/) | Vercept | Released (2025) | Advanced human-computer interaction; works with existing applications | Desktop |

## Open Source Agents

| Name | Developer | License | Key Features | Environment |
|------|-----------|---------|-------------|-------------|
| [Agent S](https://github.com/simular-ai/Agent-S) | Simular AI | Research License | Web research, content summarization, data extraction | Browser, Desktop |
| [Agent S2](https://github.com/simular-ai/Agent-S) | Simular AI | Research License | OSWorld: 34.5%; AndroidWorld: 50%; outperforms OpenAI CUA/Operator | Browser, Desktop, Phone |
| [AutoGen](https://github.com/microsoft/autogen) | Microsoft | MIT | Agents can converse with each other to solve tasks | Browser |
| [AutoGPT](https://github.com/Significant-Gravitas/Auto-GPT) | Significant Gravitas | MIT | Pioneer in autonomous GPT agents; self-prompting with memory | Browser |
| [BabyAGI](https://github.com/yoheinakajima/babyagi) | Yohei Nakajima | MIT | Autonomous task creation and prioritization | Browser |
| [Browser Use](https://browser-use.com/) | Y Combinator/ETH Zurich | Proprietary | Makes websites more digestible for AI agents | Browser |
| [c/ua (Computer-Use Agent)](https://github.com/trycua/cua) | TryCua | Open Source | High-performance virtualization; fully isolated virtual environments | Desktop, Virtual Machine |
| [CogAgent](https://arxiv.org/abs/2307.13854) | Tsinghua Univ. & Zhipu | Research License (CC BY-NC) | High-performance open model rivaling closed models | Desktop, Browser |
| [CrewAI](https://github.com/joaomdmoura/crewAI) | CrewAI | Proprietary | Enables orchestration of specialized agents in teams | Browser |
| [HyperAgent](https://github.com/FSoft-AI4Code/HyperAgent) | FSoft-AI4Code | Apache 2.0 | Handles GitHub issue resolution, repository-level code generation | Browser, Desktop |
| [LangGraph](https://github.com/langchain-ai/langgraph) | LangChain | MIT | Framework for building stateful, multi-agent systems | Browser |
| [LLM Agents](https://github.com/NVlabs/llm-agents) | NVIDIA/Meta | Research License | Standardized evaluation for LLM agents | Browser |
| [Octo](https://octo-models.github.io/) | Google DeepMind | Apache 2.0 | Zero-shot generalization to new objects and tasks | Physical World |
| [OpenInterpreter](https://github.com/OpenInterpreter/open-interpreter) | Open Interpreter | Proprietary | Code interpreter for local execution | Desktop, Browser |
| [OWL](https://github.com/camel-ai/agent) | Camel-AI | Proprietary | Distributed task automation | Browser |
| [RooCode](https://github.com/RooCode/RooCode) | Open-source | Proprietary | Autonomous coding in VS Code | Browser, Desktop |
| [Simular AI](https://github.com/simular-ai/Agent-S) | Simular | Research License | SOTA on OSWorld and AndroidWorld benchmarks | Desktop, Browser, Phone |
| [Suna](https://github.com/kortix-ai/suna) | Kortix | Proprietary | Highly versatile generalist agent; handles complex tasks | Browser |
| [UI-TARS](https://arxiv.org/abs/2407.13063) | ByteDance/TikTok | Research License | Autonomous GUI execution on PC/Mac/Android | Browser, Desktop, Phone |
| [Vercel AI SDK Computer Use](https://vercel.com/templates/next.js/ai-sdk-computer-use) | Vercel | Open Source | Standardized API for different AI models; streaming capabilities | Browser, Web |
| [WebVoyager](https://arxiv.org/abs/2401.13919) | Hongliang He et al. | Research License | 59.1% success on 15-website benchmark | Browser |
| [Felluo AI](https://felluo.ai) | Felluo | Proprietary | Vision-based GUI automation | Browser, Desktop |

## Research Projects

| Name | Institution | Focus Area | Release Date |
|------|------------|------------|-------------|
| [Deep Research Agent](https://arxiv.org/abs/2307.13854) | OpenAI | Web browsing, research | 2024 |
| [Gato](https://deepmind.google/discover/blog/a-generalist-agent/) | Google DeepMind | Multi-modal, multi-task, multi-embodiment | 2022 |
| [HuggingGPT (Jarvis)](https://arxiv.org/abs/2303.17580) | Microsoft | Orchestrates specialists for multi-modal tasks | 2023 |
| [I-AFM](https://www.microsoft.com/en-us/research/publication/interactive-agent-foundation-model/) | Microsoft Research | Multi-modal, multi-task system | 2024 |
| [Magma](https://microsoft.github.io/Magma/) | Microsoft Research | Vision-language-action model | 2025 |
| [mlejva's Computer Agent](https://x.com/mlejva/status/1900582528093995279) | Vasek Mlejnsky | GUI interaction | 2024 |
| [PaLM-E](https://palm-e.github.io/) | Google DeepMind & Robotics at Google | Embodied multimodal language model | 2023 |
| [RT-2](https://robotics-transformer2.github.io/) | Google DeepMind | Vision-language-action model | 2023 |
| [SayCan](https://arxiv.org/abs/2204.01691) | Google | Grounded language model for robotics | 2022 |
| [SIMA](https://deepmind.google/discover/blog/sima-generalist-ai-agent-for-3d-virtual-environments/) | Google DeepMind | 3D virtual environments | 2024 |
| [WebAgent](https://arxiv.org/abs/2307.13854) | Google DeepMind | Autonomous web browsing and form-filling | 2024 |

## By Environment

### Browser-Based Agents

Browser-based agents specialize in navigating and interacting with web interfaces:

| Name | Developer | Status | Development Type |
|------|-----------|--------|------------------|
| [Hyperbrowser](https://www.hyperbrowser.ai/) | Hyperbrowser.ai (YC Backed) | Released | Commercial |
| [Perplexity Comet](https://www.perplexity.ai/comet) | Perplexity AI | Upcoming | Commercial |
| [Browser Use](https://browser-use.com/) | Y Combinator/ETH Zurich | Released | Commercial, Open-source |
| [CloudCruise](https://www.cloudcruise.com/) | CloudCruise | Released | Commercial |
| [Deep Research Agent](https://arxiv.org/abs/2307.13854) | OpenAI | Unreleased | Commercial, Research |
| [Felluo AI](https://felluo.ai) | Felluo | Released | Commercial |
| [Google Mariner](https://deepmind.google/discover/blog/introducing-mariner-ai/) | Google DeepMind | Unreleased | Commercial, Research |
| [Gumloop](https://www.gumloop.com/) | Gumloop | Released | Commercial |
| [MultiOn (now Please AI)](https://please.com/) | Please AI | Released | Commercial |
| [Proxy](https://www.proxyagent.ai/) | Convergence AI | Released | Commercial |
| [Suna](https://github.com/kortix-ai/suna) | Kortix | Released | Open-source |
| [WebVoyager](https://arxiv.org/abs/2401.13919) | Hongliang He et al. | Released | Research, Open-source |

### Desktop Agents

Desktop agents interact with operating system GUIs and desktop applications:

| Name | Developer | Status | Development Type |
|------|-----------|--------|------------------|
| [Ace](https://generalagents.com/ace/) | General Agents | Upcoming | Commercial, Research |
| [Claude Computer Use](https://www.anthropic.com/news/claude-computer-use) | Anthropic | Released | Commercial |
| [Felluo AI](https://felluo.ai) | Felluo | Released | Commercial |
| [Fuyu-Heavy](https://www.adept.ai/blog/adept-fuyu-heavy) | Adept AI | Released | Commercial, Research |
| [Highlight AI](https://highlight.run/) | Embedded Intelligence | Released | Commercial |
| [OpenAI CUA (Operator)](https://openai.com/index/cua-preview/) | OpenAI | Released | Commercial |
| [Project Jarvis](https://ai.google/discover/jarvis/) | Google | Rumored | Commercial, Research |
| [CogAgent](https://arxiv.org/abs/2307.13854) | Tsinghua Univ. & Zhipu | Released | Research, Open-source |
| [Vy](https://vercept.com/) | Vercept | Released | Commercial |
| [c/ua (Computer-Use Agent)](https://github.com/trycua/cua) | TryCua | Released | Open Source |

### Physical World Agents

These agents operate in 3D environments, games, and physical systems:

| Name | Developer | Status | Development Type |
|------|-----------|--------|------------------|
| [Gato](https://deepmind.google/discover/blog/a-generalist-agent/) | Google DeepMind | Released | Research |
| [I-AFM](https://www.microsoft.com/en-us/research/publication/interactive-agent-foundation-model/) | Microsoft Research | Released | Research |
| [Magma](https://microsoft.github.io/Magma/) | Microsoft Research | Released | Research, Open Source |
| [Octo](https://octo-models.github.io/) | Google DeepMind | Released | Open Source, Research |
| [PaLM-E](https://palm-e.github.io/) | Google DeepMind & Robotics at Google | Released | Research |
| [RT-2](https://robotics-transformer2.github.io/) | Google DeepMind | Released | Research |
| [SayCan](https://arxiv.org/abs/2204.01691) | Google | Released | Research |
| [SIMA](https://deepmind.google/discover/blog/sima-generalist-ai-agent-for-3d-virtual-environments/) | Google DeepMind | Released | Research |

### Cloud Agents

Cloud-based agents running in remote environments:

| Name | Developer | Status | Development Type |
|------|-----------|--------|------------------|
| [CloudCruise](https://www.cloudcruise.com/) | CloudCruise | Released | Commercial |

### Multi-Device Agents

Agents that can operate across multiple device types:

| Name | Developer | Status | Supported Devices |
|------|-----------|--------|-------------------|
| [Agent S2](https://github.com/simular-ai/Agent-S) | Simular AI | Released | Windows, MacOS, Linux, Android, iOS |
| [AskUI Vision Agent](https://www.askui.com/) | AskUI | Released | Windows, MacOS, Linux, Android, iOS |
| [Claude Computer Use](https://www.anthropic.com/news/claude-computer-use) | Anthropic | Released | Windows, MacOS, Linux, Multi-device |
| [Manus](https://monica.im/) | Monica AI (China) | Released | Windows, MacOS, Linux, Android, iOS |
| [Simular AI](https://github.com/simular-ai/Agent-S) | Simular | Released | Windows, MacOS, Linux, Android, iOS |
| [UI-TARS](https://arxiv.org/abs/2407.13063) | ByteDance/TikTok | Released | Windows, MacOS, Linux, Android, iOS |

## By Task Complexity

*For a full breakdown of agents by task complexity, including Single Workflow, Multiple Workflow, and Complex Workflow Agents, please visit our website: [supernalintelligence.com](https://www.supernalintelligence.com/)*

## Resources

### Communities

- [Supernal Intelligence Discord](https://discord.gg/J9pU82wP) - Join our community to discuss GUI agents, share resources, and connect with others
- [X/Twitter: @supernalasi](https://x.com/supernalasi) - Follow for updates and news about GUI agents and AI advancements
- [Website: supernalintelligence.com](https://www.supernalintelligence.com/) - Official website with more resources and information

### Related Awesome Lists

- [Awesome AI Agent Leaderboards](https://github.com/supernalintelligence/Awesome-General-Agents-Leaderboard) - Comprehensive list of leaderboards for AI agents
- [Awesome AI Agent Benchmarks](https://github.com/supernalintelligence/Awesome-General-Agents-Benchmark-) - Comprehensive list of benchmarks for AI agents

### Contribution

Contributions welcome! Please read the [contribution guidelines](contributing.md) first or email [i@supernal.ai](mailto:i@supernal.ai) if you see an error or want to contribute.

## License

This awesome list is maintained by [Parni](https://x.com/ParnianBrk) and [Ian](https://x.com/ian_derrington), and is released under the MIT Open Source License.

Awesome-Gui-Agents

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README