[](https://dr.miromind.ai/)
[](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1)
[](https://miromind.ai/blog/miroflow)
[](https://github.com/MiroMindAI)
[](https://discord.com/invite/GPqEnkzQZd)
### π [Try Demo](https://dr.miromind.ai/) ο½ [δΈζ](README_zh.md) ο½ [ζ₯ζ¬θͺ](README_ja.md)
---
This repo is the official implementation of the **MiroMind Research Agent Project**. It is a leading-performance, fully open-source system designed to perform multi-step internet research for addressing complex challenges such as future event prediction. The project currently comprises four key components:
- π€ **MiroFlow**: an open-source research agent framework that offers reproducible state-of-the-art performance on representative benchmarks (e.g., FutureX, GAIA, HLE, xBench-DeepSearch, and BrowserComp benchmarks), included in this repo. See [[Get Started in Under 5 Minutes]](#-get-started-in-under-5-minutes) for a quick start.
- π€ **MiroThinker**: an open-source agent that natively supports tool-assisted reasoning. See [MiroThinker](https://github.com/MiroMindAI/mirothinker).
- π **MiroVerse**: 147k premium open-source training data supporting research agent training. See [MiroVerse](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1).
---
## π Table of Contents
- π° [News & Updates](#-news--updates)
- π [Get Started in Under 5 Minutes](#-get-started-in-under-5-minutes)
- π€ [What is MiroFlow?](#-what-is-miroflow)
- π [Highlights](#-Highlights)
- π [Performance on Benchmarks](#-performance-on-benchmarks)
- π§ [Supported Models & Tools](#-supported-models--tools)
- β [FAQ](#-faq)
- π€ [Contributing](#-contributing)
- π [License](#-license)
- π [Acknowledgments](#-acknowledgments-and-contributors)
---
## π° News & Updates
- **[2025-09-15]**: ππ **MiroFlow v0.3**: Enhanced codebase architecture and significantly improved benchmark performance, boosting GPT-5's prediction accuracy for future events by 11%.
MiroFlow now ranks #1 in the future prediction benchmark. See [FutureX](https://futurex-ai.github.io/).
- **[2025-08-27]**: **MiroFlow v0.2**: Achieves state-of-the-art performance across [multiple agentic benchmarks](https://miromind.ai/blog/miroflow), 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](docs/public_trace.md) (73.94% pass@1) and [Gradio Demo](https://github.com/MiroMindAI/MiroThinker/tree/main/apps/gradio-demo) for local deployment.
- **[2025-08-08]**: **MiroFlow v0.1**: Complete open-source release of the research agent framework.
---
## π Get Started in Under 5 Minutes
### π Prerequisites
- **Python**: 3.12 or higher
- **Package Manager**: [`uv`](https://docs.astral.sh/uv/)
- **Operating System**: Linux, macOS
### β‘ Quick Setup
**Example**: Intelligent document analysis with file processing capabilities.
```bash
# 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_reading --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"
```
π **Expected Output:** Your agent should return **\boxed{Congo Democratic Republic}** π
> **π‘ Tip:** If you encounter issues, check that your API key is correctly set in the `.env` file and that all dependencies are installed.
---
## π€ What is MiroFlow?
MiroFlow is a high-performance, modular framework for building intelligent AI agents that deliver state-of-the-art results on complex reasoning tasks like future event prediction. 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 framework](https://miromindai.github.io/MiroFlow/core_concepts/).
Research Assistant Demo -
Read CVPR 2025 Best Paper and Provide Research Advice
|
---
## π Highlights
- **Reproducible State-of-the-Art Performance**: #1 ranking across [multiple representative agentic benchmarks](https://miromindai.github.io/MiroFlow/evaluation_overview/), including FutureX, GAIA, HLE, xBench-DeepSearch, and BrowserComp benchmarks)
- **High Concurrency & Reliability**: Built with robust concurrency management and fault-tolerant design, MiroFlow efficiently handles rate-limited APIs and unstable networks, ensuring seamless trajectory collection and reliable execution of complex tasks.
- **Cost-Effective Deployment**: Powered by the open-source MiroThinker model, MiroFlow can run a research agent service on a single RTX 4090. The entire stack relies on free, open-source tools, making it simple to deploy, scale, and reproduce. See [MiroThinker](https://github.com/MiroMindAI/mirothinker).
---
## π§ Supported Models & Tools
- **Models**: GPT, Claude, Gemini, Qwen, etc.
- **Tools**: [Audio Transcription](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/audio_mcp_server.py), [Python](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/python_server.py), [File Reading](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/reading_mcp_server.py), [Reasoning](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/reasoning_mcp_server.py), [Google Search](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/searching_mcp_server.py), [VQA](https://github.com/MiroMindAI/MiroFlow/blob/miroflow-v0.3/src/tool/mcp_servers/vision_mcp_server.py), E2B, etc.
---
## π Performance on Benchmarks
We achieved the #1 ranking on the FutureX Benchmark Leaderboard as of September 10, 2025, boosting GPT-5's prediction accuracy for future events by 11%.
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% |
Follow our detailed guides to reproduce benchmark results in our [Benchmarks Documentation](https://miromindai.github.io/MiroFlow/evaluation_overview/)
---
## β 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.
---
## π€ Contributing
We welcome contributions from the community! Whether you're fixing bugs, adding features, or improving documentation, your help is appreciated.
- π **Issues**: Report bugs or request features via [GitHub Issues](https://github.com/MiroMindAI/MiroFlow/issues).
- π **Pull Requests**: Submit improvements via pull requests.
- π¬ **Discussions**: Join our [Discord community](https://discord.com/invite/GPqEnkzQZd) for questions and discussions.
## π License
This project is licensed under the Apache License 2.0.
## π Acknowledgments
**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!
## References
```
@article{miromind2025mirothinker,
title={MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling},
author={MiroMind Team and Bai, Song and Bing, Lidong and Chen, Carson and Chen, Guanzheng and Chen, Yuntao and Chen, Zhe and Chen, Ziyi and Dong, Xuan and others},
journal={arXiv preprint arXiv:2511.11793},
year={2025}
}
```
