MiroMindAI / MiroFlow

MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

🚀 Try our Demo! | 📚 Full Documentation｜中文｜日本語

Research Assistant Demo - Read CVPR 2025 Best Paper and Provide Research Advice Demo-Research-Assistant.mp4

📋 Table of Contents

• 📰 News & Updates
• 🤖 What is MiroFlow?
• ✨ Performance on Benchmarks
• 🚀 Get Started in Under 5 Minutes
• 🤖 MiroFlow Framework
• 🤝 Contributing
• ❓ FAQ
• 📄 License & Support
• 👥 Acknowledgments

📰 News & Updates

• [2025-09-15]: 🎉🎉 MiroFlow v0.3 - Enhanced codebase architecture and significantly improved benchmark performance. MiroFlow now ranks #1 in the future prediction benchmark.
• [2025-08-27]: MiroFlow v0.2 - Achieves state-of-the-art performance across multiple agentic benchmarks, including HLE (27.2%), HLE-Text-Only (29.5%), BrowserComp-EN (33.2%), BrowserComp-ZH (47.1%), and xBench-DeepSearch (72.0%)
• [2025-08-26]: Released GAIA Validation Trace (73.94% pass@1) and Gradio Demo for local deployment
• [2025-08-08]: 🎉 MiroFlow v0.1 - Complete open-source release of framework, models, and training data

---

🤖 What is MiroFlow?

MiroFlow is a comprehensive framework for building intelligent AI agents that achieve state-of-the-art performance on complex reasoning tasks. It provides enhanced conversation management, flexible tool integration, and extensive benchmark evaluations across multiple datasets.

MiroThinker is the open-source agentic model series built on this framework.

🌟 Key Highlights

• 🏆 State-of-the-Art Performance: #1 ranking across multiple agentic benchmarks
• 📊 Premium Training Data: Curated datasets via MiroVerse
• 🤖 Open Models: Complete collection at MiroThinker
• 🔧 Full Training Stack: SFT/DPO recipes at MiroTrain
• 🎯 Advanced RL: Reinforcement learning via MiroRL

✨ Performance on Benchmarks

We achieved the #1 ranking on the FutureX Benchmark Leaderboard as of September 10, 2025.

We benchmark MiroFlow on a series of benchmarks including GAIA, HLE, BrowseComp and xBench-DeepSearch and achieved SOTA results.

Model/Framework	GAIA Val	HLE	HLE-Text	BrowserComp-EN	BrowserComp-ZH	xBench-DeepSearch
MiroFlow	82.4%	27.2%	29.5%	33.2%	47.1%	72.0%
OpenAI Deep Research	67.4%	26.6%	-	51.5%	42.9%	-
Gemini Deep Research	-	26.9%	-	-	-	50+%
Kimi Researcher	-	-	26.9%	-	-	69.0%
WebSailor-72B	55.4%	-	-	-	30.1%	55.0%
Manus	73.3%	-	-	-	-	-
DeepSeek v3.1	-	-	29.8%	-	-	71.2%

🚀 Get Started in Under 5 Minutes

Clone the repository, configure your API key, and run your first intelligent agent. You'll just need one OPENROUTER_API_KEY.

📋 Prerequisites

• Python: 3.12 or higher
• Package Manager: uv
• Operating System: Linux, macOS

⚡ Quick Setup

Example: Intelligent document analysis with file processing capabilities.

# 1. Clone and setup
git clone https://github.com/MiroMindAI/MiroFlow && cd MiroFlow
uv sync

# 2. Configure API key
cp .env.template .env
# Edit .env and add your OPENROUTER_API_KEY

# 3. Run your first agent
uv run main.py trace --config_file_name=agent_quickstart_1 --task="What is the first country listed in the XLSX file that have names starting with Co?" --task_file_name="data/FSI-2023-DOWNLOAD.xlsx"

🎉 Expected Output: Your agent should return \boxed{Congo Democratic Republic} 😊

💡 Tip: If you encounter issues, check that your API key is correctly set in the .env file and that all dependencies are installed.

🎯 Comprehensive Benchmark Suite:

• GAIA Validation: A benchmark for General AI Assistants. (paper)
• GAIA-Text-103: A subset of GAIA Validation for text-only tasks. (paper)
• HLE: Humanity's Last Exam. (paper)
• HLE-Text-500: A subset of HLE for text-only tasks. (paper)

Follow our detailed guides to reproduce benchmark results in our Benchmarks Documentation

🤖 MiroFlow: AI Agentic Foundation Framework

MiroFlow is a high-performance, modular framework for building intelligent AI agents that deliver state-of-the-art results on complex reasoning tasks. The framework features advanced multi-turn conversation capabilities, extensive tool ecosystem integration, and hierarchical sub-agent orchestration for optimal task completion. Learn more about our agent workflow architecture.

🤝 Contributing

We welcome contributions from the community! Whether you're fixing bugs, adding features, or improving documentation, your help is appreciated.

• 📋 Issues: Report bugs or request features via GitHub Issues
• 🔀 Pull Requests: Submit improvements via pull requests
• 💬 Discussions: Join our Discord community for questions and discussions

❓ FAQ

What API keys do I need?

You only need an OpenRouter API key to get started. OpenRouter provides access to multiple language models through a single API.

Can I use other language models besides OpenRouter?

Yes, MiroFlow supports various language models. Check our documentation for configuration details.

How do I reproduce the benchmark results?

Follow our detailed Benchmarks Documentation for step-by-step reproduction guides.

Is there commercial support available?

For commercial inquiries and enterprise support, please contact us through our website.

📄 License & Support

This project is licensed under the Apache License 2.0.

References

Technical report is coming soon!

@misc{2025mirothinker,
    title={MiroFlow: An Open-Source Agentic Framework for Deep Research},
    author={MiroMind AI Team},
    howpublished={\url{https://github.com/MiroMindAI/MiroFlow}},
    year={2025}
}

👥 Acknowledgments and Contributors

• Benchmark Contributors for the comprehensive evaluation datasets
• Open Source Community for the tools and libraries that make this possible

We thank all contributors who have helped make MiroFlow better:

Join our community and help us build the future of AI agents!