AI Skill Hub 推荐使用:国京学生器器会 是一款优质的AI工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
因会学生器器会,输入一个因会LLM,输入一个因会学生器器会!
国京学生器器会 是一款基于 TypeScript 开发的开源工具,专注于 installable、ai、anthropic 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
因会学生器器会,输入一个因会LLM,输入一个因会学生器器会!
国京学生器器会 是一款基于 TypeScript 开发的开源工具,专注于 installable、ai、anthropic 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:npm 全局安装 npm install -g gymcoach # 方式二:npx 直接运行(无需安装) npx gymcoach --help # 方式三:项目依赖安装 npm install gymcoach # 方式四:从源码运行 git clone https://github.com/Julien-Au/gymcoach cd gymcoach npm install npm start
# 命令行使用
gymcoach --help
# 基本用法
gymcoach [options] <input>
# Node.js 代码中使用
const gymcoach = require('gymcoach');
const result = await gymcoach.run(options);
console.log(result);
# gymcoach 配置说明 # 查看配置选项 gymcoach --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export GYMCOACH_CONFIG="/path/to/config.yml"
Open source, self hosted training tracker with a built in AI coach. Log your sessions, track your progress, and get evidence based weekly debriefs and program suggestions from the LLM of your choice (Anthropic Claude or any OpenRouter model).
<p align="center"> <a href="https://demo-gymcoach.mesureprivee.com"><b>▶ Try the live demo</b></a> · login <code>demo@gymcoach.app</code> / <code>gymcoachdemo</code> </p>
<p align="center"> <img src="docs/screenshots/session.gif" width="280" alt="Logging a session in GymCoach" /> </p>
<p align="center"> <img src="docs/screenshots/home.png" width="23%" alt="Dashboard" /> <img src="docs/screenshots/progress.png" width="23%" alt="Progress charts" /> <img src="docs/screenshots/program-generator.png" width="23%" alt="AI program generator" /> <img src="docs/screenshots/catalog.png" width="23%" alt="Exercise catalog" /> </p>
Why GymCoach? It is the only workout tracker you self-host that brings your own LLM. Log your training, see your progress, and get a coach that actually knows your data: weekly debriefs, a streaming chat, and full programs generated from a sentence. Your data stays in your database; the AI runs on your Anthropic or OpenRouter key.
Status: actively developed. Multi-user, provider-agnostic (Anthropic or OpenRouter), with a unit / integration / E2E test suite and deep AI integration.
- Multi-user accounts: sign up, profiles, per-user data isolation - Workout logging with sets, reps, RIR, warmups and drop sets - plus shorthand quick entry (100x8@9), a rest timer, a plate-loading calculator, and a warm-up ramp calculator right in the set logger - Progress charts: estimated 1RM trends, weekly volume per muscle group with MEV/MRV landmark bands, a training-consistency calendar, and personal-record badges in session and on the post-session summary - Stalled-lift detection plus a deload-week recommendation derived from your stalls and readiness trend - and a one-tap planned deload week that lightens every suggested load by 10% until it expires - Per-exercise target goals (weight x reps) with a progress bar and an achieved badge - Bodyweight tracking with a trend chart - and bodyweight-aware tonnage for pull-ups, dips, etc. - Optional pre-session readiness/soreness check-in that auto-regulates suggested loads and explains why a load was held or reduced - Built-in program templates (5/3/1 BBB, GZCLP, nSuns, PPL, Upper/Lower, Starting Strength, StrongLifts 5x5, Madcow, PHUL, PHAT, Full Body), runnable as written and editable like any program - AI coach: weekly debrief and assisted program adjustments, aware of your goals and fatigue signals - Conversational AI coach: streaming chat grounded in your training data - including mid-session, with the live workout (sets so far, targets, today's readiness) attached in one tap - AI program generation from a natural-language goal, editable before saving - Pluggable LLM provider: Anthropic SDK or any OpenRouter model - Import your training history from a Strong or Hevy CSV export (dry-run preview, duplicate-safe); export everything back out as CSV anytime - Train in kilograms or pounds, a per-user preference (data is always stored in kg) - Installable PWA with offline session logging
npm install
docker compose -f docker-compose.test.yml up -d DATABASE_URL=postgresql://gymcoach_test:gymcoach_test@localhost:5434/gymcoach_test \ npx prisma migrate deploy npm run test:integration npm run build && npm run test:e2e docker compose -f docker-compose.test.yml down ```
CI (.github/workflows/ci.yml) runs lint, typecheck, unit, integration, build and E2E on every push and pull request.
A production stack is provided through docker-compose.prod.yml (app + Postgres). Put it behind a reverse proxy (Nginx, Caddy, Traefik) for HTTPS.
```bash cp .env.example .env
Set NEXT_PUBLIC_DEMO_MODE=true (plus the throwaway demo credentials) in the instance's .env, then build with the demo profile and run the one-shot seeder. It fills the demo account with a rich deterministic dataset (12 weeks of sessions, a bodyweight trend, a goal, readiness check-ins); re-running it on every deploy also resets whatever visitors changed.
docker compose -f docker-compose.prod.yml --profile demo up -d --build
docker compose -f docker-compose.prod.yml --profile demo run --rm seed-demo
Recommended setup: Postgres in Docker, Next.js running locally for hot reload.
```bash
npm run db:seed
cp .env.example .env
All configuration is done through environment variables. See .env.example for the full list (database, JWT secret, demo account, and the AI provider keys).
因会学生器器会很有有一个因会学生器器会,很有一个因会LLM,输入丁个因会学生器器会!
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,国京学生器器会 是一款质量良好的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | gymcoach |
| 原始描述 | 开源AI工具:Self-hosted AI workout tracker. Bring your own LLM (Anthropic or OpenRouter): we。⭐11 · TypeScript |
| Topics | installableaianthropicclaudefitnessllmtypescript |
| GitHub | https://github.com/Julien-Au/gymcoach |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-10 · 更新时间:2026-06-10 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。