 
教练
一款基于Strava数据的开源智能健身和健康私人教练。
特性
- 人工智能驱动的教练:获得由高级LLM提供的智能培训建议
- Strava集成:从Strava自动分析您的训练
- 锻炼分析:收到详细的反馈和个性化建议
- 培训计划:根据您的目标和健身水平制定定制计划
- 会话界面:与你的人工智能培训师自然地讨论训练、恢复和表现
快速开始
先决条件
安装
- 克隆并安装:
git clone https://github.com/Joe-Heffer/trainer.git
cd trainer
pip install -e .- 设置Strava MCP服务器:
# Clone and build the Strava MCP server
git clone https://github.com/r-huijts/strava-mcp.git
cd strava-mcp
npm install
npm run build
# Authenticate with Strava (creates API app and gets tokens)
npx tsx scripts/setup-auth.ts
# Follow the prompts to authorize with Strava- 配置环境:
cd ../trainer
cp .env.example .env
# Edit .env and add:
# - GOOGLE_API_KEY: Your Google Gemini API key (https://aistudio.google.com/apikey)
# - STRAVA_MCP_PATH: Absolute path to strava-mcp/dist/server.js示例 .env:
GOOGLE_API_KEY=your_gemini_api_key_here
STRAVA_MCP_PATH=/absolute/path/to/strava-mcp/dist/server.js
LOG_LEVEL=WARNING用法
命令行
trainer对于论点:
trainer --help程序化
from trainer import TrainerAgent
agent = TrainerAgent()
await agent.initialize()
# Analyze a workout
analysis = await agent.analyze_workout("activity_id")
# Create a training plan
plan = await agent.create_training_plan(
goal="Run a half marathon under 2 hours",
weeks=12
)对话示例
💪> What should I do to improve my cycling performance?
Based on your Strava data, here's what I see:
- You've been cycling consistently with multiple rides per week
- Your distances vary from 7km to 80km
- You're incorporating regular weight training which supports cycling performance
Recommendations:
1. **Structured Training Zones:** Add interval training to improve VO2 max
2. **Progressive Overload:** Gradually increase ride duration and intensity
3. **Strength Training:** Continue your weight training - it's great for power
4. **Recovery:** Ensure adequate rest between hard efforts
5. **Nutrition:** Focus on pre-ride and during-ride fueling for longer sessions
Would you like me to create a specific training plan for your cycling goals?
💪> quit
👋 Thanks for training with trAIner!文档
对于用户:
对于贡献者:
贡献
我们欢迎捐款!看 贡献.md 开始吧。
支持
- 问题:
- 讨论:
许可证
MIT许可证-请参阅 许可证 了解详情。
致谢
内置:
- 谷歌代理开发工具包(ADK)
- 模型上下文协议(MCP)
- r-huijts/strava-mcp -Strava MCP服务器
- API斯特拉瓦
