MiroFlow Project
How to install miroflow?
miromindai/miroflow
$git clone https://github.com/miromindai/miroflowInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install miroflow by running `git clone https://github.com/miromindai/miroflow`, then use it for the current task and follow its documentation at https://github.com/miromindai/miroflow.
README.md
| 1 | <div align="center"> |
| 2 | <img src="docs/mkdocs/docs/assets/miroflow_logo.png" width="45%" alt="MiroFlow" /> |
| 3 | </div> |
| 4 | |
| 5 | <br> |
| 6 | |
| 7 | |
| 8 | <div align="center"> |
| 9 | |
| 10 | [](https://dr.miromind.ai/) |
| 11 | [](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1) |
| 12 | [](https://miromind.ai/blog/miroflow) |
| 13 | |
| 14 | [](https://github.com/MiroMindAI) |
| 15 | [](https://discord.com/invite/GPqEnkzQZd) |
| 16 | |
| 17 | </div> |
| 18 | |
| 19 | <div align="center"> |
| 20 | |
| 21 | ### 🚀 [Try Demo](https://dr.miromind.ai/) ｜ [中文](README_zh.md) ｜ [日本語](README_ja.md) |
| 22 | |
| 23 | </div> |
| 24 | |
| 25 | <div align="center"> |
| 26 | <img width="100%" alt="image" src="docs/mkdocs/docs/assets/futurex-09-12.png" /> |
| 27 | </div> |
| 28 | |
| 29 | --- |
| 30 | |
| 31 | 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: |
| 32 | |
| 33 | - 🤖 **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. |
| 34 | - 🤔 **MiroThinker**: an open-source agent that natively supports tool-assisted reasoning. See [MiroThinker](https://github.com/MiroMindAI/mirothinker). |
| 35 | - 📊 **MiroVerse**: 147k premium open-source training data supporting research agent training. See [MiroVerse](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1). |
| 36 | |
| 37 | --- |
| 38 | |
| 39 | ## 📋 Table of Contents |
| 40 | |
| 41 | - 📰 [News & Updates](#-news--updates) |
| 42 | - 🚀 [Get Started in Under 5 Minutes](#-get-started-in-under-5-minutes) |
| 43 | - 🤖 [What is MiroFlow?](#-what-is-miroflow) |
| 44 | - 🌟 [Highlights](#-Highlights) |
| 45 | - 📈 [Performance on Benchmarks](#-performance-on-benchmarks) |
| 46 | - 🔧 [Supported Models & Tools](#-supported-models--tools) |
| 47 | - ❓ [FAQ](#-faq) |
| 48 | - 🤝 [Contributing](#-contributing) |
| 49 | - 📄 [License](#-license) |
| 50 | - 🙏 [Acknowledgments](#-acknowledgments-and-contributors) |
| 51 | |
| 52 | --- |
| 53 | |
| 54 | ## 📰 News & Updates |
| 55 | |
| 56 | - **[2025-09-15]**: 🎉🎉 **MiroFlow v0.3**: Enhanced codebase architecture and significantly improved benchmark performance, boosting GPT-5's prediction accuracy for future events by 11%. |
| 57 | MiroFlow now ranks #1 in the future prediction benchmark. See [FutureX](https://futurex-ai.github.io/). |
| 58 | - **[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%). |
| 59 | - **[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. |
| 60 | - **[2025-08-08]**: **MiroFlow v0.1**: Complete open-source release of the research agent framework. |
| 61 | |
| 62 | --- |
| 63 | |
| 64 | ## 🚀 Get Started in Under 5 Minutes |
| 65 | |
| 66 | ### 📋 Prerequisites |
| 67 | |
| 68 | - **Python**: 3.12 or higher |
| 69 | - **Package Manager**: [`uv`](https://docs.astral.sh/uv/) |
| 70 | - **Operating System**: Linux, macOS |
| 71 | |
| 72 | ### ⚡ Quick Setup |
| 73 | |
| 74 | **Example**: Intelligent document analysis with file processing capabilities. |
| 75 | |
| 76 | ```bash |
| 77 | # 1. Clone and setup |
| 78 | git clone https://github.com/MiroMindAI/MiroFlow && cd MiroFlow |
| 79 | uv sync |
| 80 | |
| 81 | # 2. Configure API key |
| 82 | cp .env.template .env |
| 83 | # Edit .env and add your OPENROUTER_API_KEY |
| 84 | |
| 85 | # 3. Run your first agent |
| 86 | uv run main.py trace --config_fi |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
