AutoAgent-Windows

AutoAgent-Windows: A Windows-Optimized Fork of
the AutoAgent LLM Framework

---

Welcome to AutoAgent-Windows! This is a Windows-optimized fork of the incredible AutoAgent framework. While AutoAgent is a fantastic framework for creating and deploying LLM agents through natural language, some users (including myself) encountered Windows compatibility issues. This fork aims to provide a smooth, Windows-first experience while maintaining all the powerful features of the original framework.

🔄 What's Different in this Fork?

• 🪟 Windows-First Development: Optimized for Windows environments with proper path handling and PowerShell compatibility
• 🛠️ Simplified Setup: Streamlined installation process for Windows users
• 🐛 Bug Fixes: Resolved various Windows-specific issues from the original framework
• 🔧 Native Tools: Adapted tool implementations to work seamlessly on Windows
• 💻 PowerShell Integration: Better command execution through PowerShell

✨ Original Features Maintained

• 🏆 Top Performer on the GAIA Benchmark
• 📚 Agentic-RAG with Native Self-Managing Vector Database
• ✨ Agent and Workflow Creation with Ease
• 🌐 Universal LLM Support
• 🔀 Flexible Interaction
• 🤖 Dynamic, Extensible, Lightweight

✨Key Features

• 🏆 Top Performer on the GAIA Benchmark
  AutoAgent has ranked the #1 spot among open-sourced methods, delivering comparable performance to OpenAI's Deep Research.

• 📚 Agentic-RAG with Native Self-Managing Vector Database
  AutoAgent equipped with a native self-managing vector database, outperforms industry-leading solutions like LangChain.

• ✨ Agent and Workflow Create with Ease
  AutoAgent leverages natural language to effortlessly build ready-to-use tools, agents and workflows - no coding required.

• 🌐 Universal LLM Support
  AutoAgent seamlessly integrates with A Wide Range of LLMs (e.g., OpenAI, Anthropic, Deepseek, vLLM, Grok, Huggingface ...)

• 🔀 Flexible Interaction
  Benefit from support for both function-calling and ReAct interaction modes.

• 🤖 Dynamic, Extensible, Lightweight
  AutoAgent is your Personal AI Assistant, designed to be dynamic, extensible, customized, and lightweight.

🚀 Unlock the Future of LLM Agents. Try 🔥AutoAgent🔥 Now!

Quick Overview of AutoAgent.

🔥 News

• [2025, Feb 17]:  🎉🎉We've updated and released AutoAgent v0.2.0 (formerly known as MetaChain). Detailed changes include: 1) fix the bug of different LLM providers from issues; 2) add automatic installation of AutoAgent in the container environment according to issues; 3) add more easy-to-use commands for the CLI mode. 4) Rename the project to AutoAgent for better understanding.
• [2025, Feb 10]:  🎉🎉We've released MetaChain!, including framework, evaluation codes and CLI mode! Check our paper for more details.

📑 Table of Contents

• ✨ Features
• 🔥 News
• 🔍 How to Use AutoAgent
  • 1. user mode (SOTA 🏆 Open Deep Research)
  • 2. agent editor (Agent Creation without Workflow)
  • 3. workflow editor (Agent Creation with Workflow)
• ⚡ Quick Start
  • Installation
  • API Keys Setup
  • Start with CLI Mode
  • WebSurfer Example
• ☑️ Todo List
• 🔬 How To Reproduce the Results in the Paper
• 📖 Documentation
• 🤝 Join the Community
• 🙏 Acknowledgements
• 🌟 Cite

🔍 How to Use AutoAgent

1. user mode (SOTA 🏆 Open Deep Research)

AutoAgent have an out-of-the-box multi-agent system, which you could choose user mode in the start page to use it. This multi-agent system is a general AI assistant, having the same functionality with OpenAI's Deep Research and the comparable performance with it in GAIA benchmark.

• 🚀 High Performance: Matches Deep Research using Claude 3.5 rather than OpenAI's o3 model.
• 🔄 Model Flexibility: Compatible with any LLM (including Deepseek-R1, Grok, Gemini, etc.)
• 💰 Cost-Effective: Open-source alternative to Deep Research's $200/month subscription
• 🎯 User-Friendly: Easy-to-deploy CLI interface for seamless interaction
• 📁 File Support: Handles file uploads for enhanced data interaction

🎥 Deep Research (aka User Mode)

2. agent editor (Agent Creation without Workflow)

The most distinctive feature of AutoAgent is its natural language customization capability. Unlike other agent frameworks, AutoAgent allows you to create tools, agents, and workflows using natural language alone. Simply choose agent editor or workflow editor mode to start your journey of building agents through conversations.

You can use agent editor as shown in the following figure.

Input what kind of agent you want to create.

Automated agent profiling.

Output the agent profiles.

Create the desired tools.

Input what do you want to complete with the agent. (Optional)

Create the desired agent(s) and go to the next step.

3. workflow editor (Agent Creation with Workflow)

You can also create the agent workflows using natural language description with the workflow editor mode, as shown in the following figure. (Tips: this mode does not support tool creation temporarily.)

Input what kind of workflow you want to create.

Automated workflow profiling.

Output the workflow profiles.

Input what do you want to complete with the workflow. (Optional)

Create the desired workflow(s) and go to the next step.

⚡ Quick Start

Installation

git clone https://github.com/prestoncn/AutoAgent-Windows.git
cd AutoAgent-Windows
pip install -e .

Docker Setup on Windows

We use Docker Desktop for Windows to containerize the agent-interactive environment. Please install Docker Desktop first.

API Keys Setup

Create an environment variable file, just like .env.template, and set the API keys for the LLMs you want to use. Not every LLM API Key is required, use what you need.

# Required Github Tokens of your own
GITHUB_AI_TOKEN=

# Optional API Keys
OPENAI_API_KEY=
DEEPSEEK_API_KEY=
ANTHROPIC_API_KEY=
GEMINI_API_KEY=
HUGGINGFACE_API_KEY=
GROQ_API_KEY=
XAI_API_KEY=

Start with CLI Mode

[🚨 News: ] We have updated a more easy-to-use command to start the CLI mode and fix the bug of different LLM providers from issues. You can follow the following steps to start the CLI mode with different LLM providers with much less configuration.

Command Options:

You can run auto main to start full part of AutoAgent, including user mode, agent editor and workflow editor. Btw, you can also run auto deep-research to start more lightweight user mode, just like the Auto-Deep-Research project. Some configuration of this command is shown below.

• --container_name: Name of the Docker container (default: 'deepresearch')
• --port: Port for the container (default: 12346)
• COMPLETION_MODEL: Specify the LLM model to use, you should follow the name of Litellm to set the model name. (Default: claude-3-5-sonnet-20241022)
• DEBUG: Enable debug mode for detailed logs (default: False)
• API_BASE_URL: The base URL for the LLM provider (default: None)
• FN_CALL: Enable function calling (default: None). Most of time, you could ignore this option because we have already set the default value based on the model name.
• git_clone: Clone the AutoAgent repository to the local environment (only support with the auto main command, default: True)
• test_pull_name: The name of the test pull. (only support with the auto main command, default: 'autoagent_mirror')

More details about git_clone and test_pull_name]

In the agent editor and workflow editor mode, we should clone a mirror of the AutoAgent repository to the local agent-interactive environment and let our AutoAgent automatically update the AutoAgent itself, such as creating new tools, agents and workflows. So if you want to use the agent editor and workflow editor mode, you should set the git_clone to True and set the test_pull_name to 'autoagent_mirror' or other branches.

auto main with different LLM Providers

Then I will show you how to use the full part of AutoAgent with the auto main command and different LLM providers. If you want to use the auto deep-research command, you can refer to the Auto-Deep-Research project for more details.

Using AutoAgent with Different LLM Providers

Below are instructions for using different LLM providers with AutoAgent-Windows. All commands are PowerShell-compatible.

Anthropic (Default)

1. Add to your .env file:

ANTHROPIC_API_KEY=your_anthropic_api_key

2. Run AutoAgent:

auto main # Uses default model claude-3-5-sonnet-20241022

OpenAI

1. Add to your .env file:

OPENAI_API_KEY=your_openai_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="gpt-4o"; auto main

Mistral

1. Add to your .env file:

MISTRAL_API_KEY=your_mistral_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="mistral/mistral-large-2407"; auto main

Gemini - Google AI Studio

1. Add to your .env file:

GEMINI_API_KEY=your_gemini_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="gemini/gemini-2.0-flash"; auto main

Huggingface

1. Add to your .env file:

HUGGINGFACE_API_KEY=your_huggingface_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="huggingface/meta-llama/Llama-3.3-70B-Instruct"; auto main

Groq

1. Add to your .env file:

GROQ_API_KEY=your_groq_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="groq/deepseek-r1-distill-llama-70b"; auto main

OpenAI-Compatible Endpoints (e.g., Grok)

1. Add to your .env file:

OPENAI_API_KEY=your_api_key_for_openai_compatible_endpoints

2. Run AutoAgent:

$env:COMPLETION_MODEL="openai/grok-2-latest"; $env:API_BASE_URL="https://api.x.ai/v1"; auto main

OpenRouter (Recommended for DeepSeek-R1)

We recommend using OpenRouter for DeepSeek-R1 access due to better API reliability.

1. Add to your .env file:

OPENROUTER_API_KEY=your_openrouter_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="openrouter/deepseek/deepseek-r1"; auto main

DeepSeek

1. Add to your .env file:

DEEPSEEK_API_KEY=your_deepseek_api_key

2. Run AutoAgent:

$env:COMPLETION_MODEL="deepseek/deepseek-chat"; auto main

After running any of these commands, you'll see the AutoAgent start page:

Start Page of AutoAgent.

Tips

Import browser cookies to browser environment

You can import the browser cookies to the browser environment to let the agent better access some specific websites. For more details, please refer to the cookies folder.

Add your own API keys for third-party Tool Platforms

If you want to create tools from the third-party tool platforms, such as RapidAPI, you should subscribe tools from the platform and add your own API keys by running process_tool_docs.py.

python process_tool_docs.py

More features coming soon! 🚀 Web GUI interface under development.

WebSurfer Example

The WebSurfer component allows AI agents to navigate and interact with web pages. To run the WebSurfer example:

python examples/websurfer_example.py

Environment Variables for WebSurfer

You can customize the WebSurfer example by setting these environment variables in a .env file:

GOOGLE_API_KEY=your_google_api_key
GOOGLE_CSE_ID=your_google_custom_search_engine_id
LOCAL_ROOT=path_to_local_root_directory
WORKPLACE_NAME=websurfer_example
TRY_COMPLEX_PAGE=false

• Set TRY_COMPLEX_PAGE=true if you want to attempt loading complex pages like W3Schools (may cause timeouts)

Troubleshooting WebSurfer

If you encounter browser-related errors:

1. For "Frame marking" warnings - these are normal for complex pages and don't affect functionality
2. For timeouts on complex pages - increase the MAX_COMPLEX_PAGE_WAIT value in the script
3. If Google search returns CAPTCHA pages - this is expected when automating searches; consider using API access instead

☑️ Todo List

AutoAgent is continuously evolving! Here's what's coming:

• 📊 More Benchmarks: Expanding evaluations to SWE-bench, WebArena, and more
• 🖥️ GUI Agent: Supporting Computer-Use agents with GUI interaction
• 🔧 Tool Platforms: Integration with more platforms like Composio
• 🏗️ Code Sandboxes: Supporting additional environments like E2B
• 🎨 Web Interface: Developing comprehensive GUI for better user experience

Have ideas or suggestions? Feel free to open an issue! Stay tuned for more exciting updates! 🚀

🔬 How To Reproduce the Results in the Paper

GAIA Benchmark

For the GAIA benchmark, you can run the following command to run the inference.

cd path/to/AutoAgent && sh evaluation/gaia/scripts/run_infer.sh

For the evaluation, you can run the following command.

cd path/to/AutoAgent && python evaluation/gaia/get_score.py

Agentic-RAG

For the Agentic-RAG task, you can run the following command to run the inference.

Step1. Turn to this page and download it. Save them to your datapath.

Step2. Run the following command to run the inference.

cd path/to/AutoAgent && sh evaluation/multihoprag/scripts/run_rag.sh

Step3. The result will be saved in the evaluation/multihoprag/result.json.

```tex @misc{AutoAgent, title={{AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents}}, author={Jiabin Tang, Tianyu Fan, Chao Huang}, year={2025}, eprint={202502.05957}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2502.05957}, } ```

For this Windows-optimized fork:

@misc{AutoAgentWindows,
      title={{AutoAgent-Windows: A Windows-Optimized Fork of the AutoAgent Framework}},
      author={Preston Nico},
      year={2024},
      url={https://github.com/prestoncn/AutoAgent-Windows},
}