Skip to main content

XINGZIER AI is a **personal assistant** that runs in your own environment.

Project description

XINGZIER AI

🤖 智能 AI 助手平台 - 支持多种 AI 模型、本地部署、飞书/Discord 等频道集成


🚀 快速上手指南(新手必读)

📖 完整安装教程docs/QUICKSTART.md

3 步快速开始

# 1. 安装
pip install xingzierai

# 2. 初始化
xingzierai init

# 3. 启动
xingzierai run

然后打开浏览器访问 http://localhost:8555


✨ 功能特性

  • 🌐 多模型支持 - OpenAI GPT-4、Anthropic Claude、Google Gemini、OpenRouter 等
  • 💻 本地模型 - 支持 llama.cpp、Ollama、Apple MLX (M1/M2/M3)
  • 📱 多频道集成 - 飞书、Discord、Telegram、微信企业版等
  • 🖥️ Web 控制台 - 友好的 Web 界面管理配置
  • 🔄 实时对话 - 支持流式输出、上下文记忆
  • 🛡️ 安全可靠 - 本地部署,数据完全自主控制

📦 安装

基本安装

pip install xingzierai

Apple Silicon Mac (M1/M2/M3)

pip install xingzierai[mlx]

完整安装(包含所有功能)

pip install xingzierai[full]

🆘 疑难解答

问题 解决方案
安装报错 点击查看常见问题
启动失败 点击查看解决方案
API 配置 点击查看配置指南

📚 完整文档


🖥️ 系统要求

项目 最低 推荐
Python 3.10 3.11/3.12
内存 4GB 8GB+
系统 Win10+, macOS 10.14+, Ubuntu 18.04+ Win11, macOS 13+, Ubuntu 22.04+

⚙️ 配置

环境变量

# API 密钥
export XINGZIERAI_API_KEY=sk-or-v1-xxxxx

# CORS 配置(允许的前端域名)
export XINGZIERAI_CORS_ORIGINS=http://localhost:8555

# LLM 超时时间(秒)
export XINGZIERAI_LLM_TIMEOUT=300

🚀 启动

# 基本启动
xingzierai run

# 指定端口
xingzierai run --port 9000

# 后台运行
nohup xingzierai run > app.log 2>&1 &

访问 http://localhost:8555 打开 Web 控制台。


🛠️ 开发

# 克隆仓库
git clone https://github.com/your-repo/xingzierai.git
cd xingzierai

# 开发模式安装
pip install -e .

# 构建发布包
python -m build

📄 许可证

MIT License


🙏 致谢


Made with ❤️ by XINGZIER AI Team

Project details


Download files

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

Source Distribution

xingzierai-0.100.0.tar.gz (11.7 MB view details)

Uploaded Source

Built Distribution

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

xingzierai-0.100.0-py3-none-any.whl (18.1 MB view details)

Uploaded Python 3

File details

Details for the file xingzierai-0.100.0.tar.gz.

File metadata

  • Download URL: xingzierai-0.100.0.tar.gz
  • Upload date:
  • Size: 11.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.13

File hashes

Hashes for xingzierai-0.100.0.tar.gz
Algorithm Hash digest
SHA256 f50d10751889c12c0f4f493f02021a7d35f53a3c9f3146ac2fe45c5840ceaba0
MD5 157da86402639fe7267c67054a01cd88
BLAKE2b-256 8ff82b3607b4cd48f265133392367fac04c820d15182990c0523fa99784e861a

See more details on using hashes here.

File details

Details for the file xingzierai-0.100.0-py3-none-any.whl.

File metadata

  • Download URL: xingzierai-0.100.0-py3-none-any.whl
  • Upload date:
  • Size: 18.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.13

File hashes

Hashes for xingzierai-0.100.0-py3-none-any.whl
Algorithm Hash digest
SHA256 eb53ec66bd155290c64f47019a3b2abddb4827d46e4829d35439b6af8611c4ff
MD5 0a4b5c4e00b3327a8b668852b481f3dc
BLAKE2b-256 75f17140504c8d5bc1c5b7cb820c7707be020b80e2dd5efeab37e04d18cb0f9c

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