Skip to main content

multimoda Agent framework

Project description

🤖 HyperAgent

一个强大的多模态智能代理框架

⚡ 特性📦 安装🚀 使用🏗️ 项目结构💡 示例说明📄 许可证


HyperAgent 是一个多模态智能代理框架,旨在创建和管理具有多种技能的智能代理。它支持通过技能扩展代理功能,提供灵活的智能体开发和部署能力。

✨ 功能特性

  • 🧠 多模态智能代理支持 - 支持多种输入输出模式
  • 🔧 可扩展的技能系统 - 通过技能轻松扩展代理功能
  • 🌐 支持 OpenAI API 兼容的模型接口 - 可使用各种 LLM 模型
  • 🛡️ 内置沙箱环境支持 - 安全执行外部代码
  • ⚙️ 可配置的工作流管理 - 灵活配置代理行为

📦 安装

环境要求

  • 🐍 Python >= 3.12

安装步骤

  1. 📥 克隆项目:

    git clone https://github.com/your-repo/HyperAgent.git
    cd HyperAgent
    
  2. 🔄 创建虚拟环境(推荐):

    python -m venv venv
    source venv/bin/activate  # Linux/Mac
    # 或
    venv\Scripts\activate     # Windows
    
  3. 📚 安装依赖:

    pip install -e .
    

🚀 使用方法

命令行方式

hyperagent

作为库使用

from hyperagent.agent.agent_skill import create_agent_skill

# 🤖 创建智能代理
agent = create_agent_skill(config)

🧪 运行示例

项目包含示例,位于 examples/agent_skills 目录下:

cd examples/agent_skills
python run.py

⚙️ 配置说明

HyperAgent 支持通过配置文件自定义代理行为。配置文件使用 OmegaConf 格式,支持以下选项:

  • work_dir: 📁 工作目录
  • skills_dir: 🔧 技能目录
  • example_data_dir: 📊 示例数据目录
  • use_sandbox: 🛡️ 是否使用沙箱环境

🔧 技能系统

HyperAgent 的技能系统允许代理执行特定任务。技能可以包括脚本、文档和资源文件。每个技能包含:

  • SKILL.md: 📝 技能说明文档
  • scripts/: 💻 可执行脚本
  • 📁 相关资源文件

🧪 开发

运行测试

# 从项目根目录运行
python -m pytest tests/

🤝 贡献

欢迎提交 Issue 和 Pull Request 来改进项目。

📄 许可证

本项目使用 GPL-3.0 许可证。详情请参见 LICENSE 文件。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

hyperagent-0.0.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (1.1 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.17+ x86-64manylinux: glibc 2.28+ x86-64

hyperagent-0.0.2-cp313-cp313-macosx_11_0_arm64.whl (689.3 kB view details)

Uploaded CPython 3.13macOS 11.0+ ARM64

hyperagent-0.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (567.6 kB view details)

Uploaded CPython 3.12manylinux: glibc 2.17+ x86-64manylinux: glibc 2.28+ x86-64

hyperagent-0.0.2-cp312-cp312-macosx_11_0_arm64.whl (353.4 kB view details)

Uploaded CPython 3.12macOS 11.0+ ARM64

File details

Details for the file hyperagent-0.0.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for hyperagent-0.0.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 5d704760ce43010369cc7a170a8b36efd490e781f183d886c2106400f6bb5022
MD5 6dc186b3fee6d0a59e25dfc93561e700
BLAKE2b-256 0b32fe3d3f2c921157c513d6f51107fa91b74734eaf7cfa9731b32e565523bbc

See more details on using hashes here.

File details

Details for the file hyperagent-0.0.2-cp313-cp313-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for hyperagent-0.0.2-cp313-cp313-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 8134b93ce2f09defdb95513145ad3d21898c0395dc01c813f8af2cdee28be6ac
MD5 24c4af8b0eba74d6c5b2e0037d001f10
BLAKE2b-256 6f19b2ea3c98735a4732190751c04071c468e831da34fe9f92a6565af24a7a20

See more details on using hashes here.

File details

Details for the file hyperagent-0.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for hyperagent-0.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 3e7a4055848d3004c49f4bad9fdc135487aa357781a3b0d0a33590ac628a99a0
MD5 79f722c1456408000023c32afc2da6ec
BLAKE2b-256 238236f3b9a2123ed2ebbab5b49ff9d8ede9c942c8af41c225981136b6f9923d

See more details on using hashes here.

File details

Details for the file hyperagent-0.0.2-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for hyperagent-0.0.2-cp312-cp312-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 f0a6cd3a280292e4e99414744b8dd58dc935a9c3ff2123577811a35500d3d1ab
MD5 afc6ef06ab9caa27ee3e840053068198
BLAKE2b-256 9d31ecefe6c8f0967f0e8e5161371e0a7dced3aa393d8b818201b37e44338f66

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page