AB
AB
AiBoss

All Categories

project

OpenManus - An open-source fork of Manus released by the MetaGPT team.

OpenManus is an open-source fork of Manus released by the MetaGPT team, providing an AI agent that requires no invitation code. OpenManus is based on a modular design, supports multiple language models and toolchains, and can execute code, process files, etc.

What is OpenManus?

OpenManus is an open-source fork of Manus from the MetaGPT team, providing an AI agent that requires no invitation code. Based on a modular design, OpenManus supports multiple language models and toolchains, enabling complex tasks such as executing code, processing files, and searching network information. OpenManus's core advantage lies in its real-time feedback mechanism, allowing users to intuitively see the AI's thought process and task execution progress. OpenManus boasts a powerful toolchain and flexible configuration options, allowing developers to easily customize it to their needs.

Main functions of OpenManus

  • Python code executor:Generate and execute code in real time to complete complex calculations and automated tasks.
  • Document processing systemSupports the generation and management of various documents.
  • Internet search toolsAutomatically retrieves network information to provide data support for tasks.
  • Browser automationSimulates human operation to complete web browsing and interactive tasks.

OpenManus's technical principles

  • LLM-based core architectureOpenManus sends user input as a prompt to the LLM. The LLM generates an answer or content based on the input. The system then returns the generated result to the user.
  • Flexible configuration mechanismUsers can select different LLM models (such as GPT-4o) based on configuration files. Configuration files support adjusting parameters (such as maximum generation length, randomness, etc.).
  • Input processing: Format or segment user input to ensure that the LLM can understand it.
  • Output processing: Optimize or filter the content generated by LLM to better meet user needs.
  • Modular designBased on a modular design, it supports a plugin mechanism, making it easy for developers to extend functionality. Switching between LLM models is done via configuration files without modifying the code.

How to use OpenManus

  • Creating a Python environmentCreate a separate Python environment to avoid dependency conflicts. Conda is recommended for environment management.
conda create -n open_manus python=3.9
# 创建环境，推荐使用 Python 3.9
conda activate open_manus # 激活环境
  • Cloning the OpenManus repositoryClone the OpenManus source code from GitHub to your local machine.
git clone https://github.com/mannaandpoe/OpenManus.git # 克隆仓库
cd OpenManus # 进入项目目录
  • Install dependenciesInstall the Python libraries required for the project.
pip install
-r requirements.txt # 安装依赖
  • configuration fileOpenManus requires a configuration file to specify the API key for the LLM (such as GPT-4) to be used and other parameters.
    • Let's start with the example configuration file:
cp config/config.example.toml config/config.toml # 复制示例配置文件
    • Edit the `config/config.toml` file, filling in your API key and other settings. For example:
# Global LLM configuration
[llm]
model
=
"gpt-4"
# 使用的模型
base_url
=
"https://api.openai.com/v1"
# API 地址
api_key
=
"sk-..."
# 替换为你的 OpenAI API 密钥
max_tokens
=
4096
# 最大生成长度
temperature
=
0.0
# 随机性
  • Running OpenManusAfter completing the above steps, run OpenManus. Run the following command in the project directory:
python main.py # 启动 OpenManus

Once running, OpenManus will call the configured LLM to return the results based on the ideas or tasks input in the terminal.

OpenManus project address

Application scenarios of OpenManus

  • Personal task automationIt helps users automate daily tasks such as file processing, information retrieval, and schedule management.
  • Developer assistanceSupports code generation, debugging, and project planning, improving development efficiency.
  • Education and LearningIt generates learning materials, assists in programming learning, and helps students and educators.
  • Enterprise-level tool developmentCustomized AI tools for enterprises, used in data analysis, customer support, and report generation.
  • Research and InnovationSupports multimodal and natural language processing research, enabling the rapid development of experimental tools.
Back