coach-memory
A personal career-coach memory service that ingests coaching logs, embeds them for semantic search, and exposes the memory to Claude clients via MCP, with a Next.js dashboard for browsing.
README
Personal Coach
A personal career-coach memory service. It ingests daily/weekly/quarterly coaching logs and notes, embeds them into Postgres (pgvector) for hybrid semantic + keyword search, and exposes that memory to Claude clients over an MCP server behind BetterAuth (OAuth + API keys). It also serves a small Next.js dashboard (timeline, search, notes capture, analytics) for browsing the same data directly.
Prerequisites
- Node.js 22+
- Docker (for the local Postgres/pgvector instance)
Local setup
- Start Postgres:
docker compose up -d - Copy/create
.env.localwith the required env vars (see below). - Apply the schema (coach tables + better-auth tables):
npm run migrate - Create a login user and a sync API key:
ALLOW_SIGNUP=true npm run create-user -- <email> <password> npm run create-api-key -- sync-cli
Environment variables
| Variable | Used by | Purpose |
|---|---|---|
DATABASE_URL |
app, migrate, scripts | Postgres connection string |
OPENAI_API_KEY |
app | Embeddings for ingest/search |
BETTER_AUTH_SECRET |
app | BetterAuth session/token signing secret |
BETTER_AUTH_URL |
app | Public base URL BetterAuth issues callbacks against |
COACH_MEMORY_URL |
sync CLI | Base URL of the Personal Coach server to sync against |
COACH_SYNC_API_KEY |
sync CLI | API key (from create-api-key) used to authenticate sync pushes/pulls |
Scripts
npm test # run the test suite (vitest, against .env.test)
npm run build # production build (next build)
npm run sync # push local docs, pull notes mirror, watermark progress
Production deploy
Coolify (recommended — one resource, no manual proxy/DB wiring)
docker-compose.coolify.yml deploys the app and its pgvector database together as a
single "Docker Compose" resource:
- In Coolify: New Resource → Docker Compose, point it at this repo, and set the
Compose file path to
docker-compose.coolify.yml. - Set two environment variables in the Coolify UI:
OPENAI_API_KEYandBETTER_AUTH_SECRET(openssl rand -hex 32). Everything else — the DB credentials, the app's public domain and TLS cert — is generated and wired automatically via Coolify'sSERVICE_FQDN/SERVICE_URLmagic variables. - Deploy. The schema applies itself on every container boot (see
scripts/docker-entrypoint.mjs), so there's no separate migrate step. - One-time bootstrap: temporarily expose the
dbservice's port (or use an SSH tunnel to the Coolify host), then from your local checkout run against thatDATABASE_URL:ALLOW_SIGNUP=true npm run create-user -- <email> <password> npm run create-api-key -- sync-cli - Connect a Claude client to
https://<the-domain-coolify-assigned>/mcp.
Any other container host
The plain Dockerfile at the repo root also builds a standalone image on its own —
point it at any pgvector/pgvector Postgres instance, set the environment variables
above, and front it with your own TLS/reverse-proxy setup (e.g. a Cloudflare
Tunnel). The image still self-migrates on boot, so no separate npm run migrate
step is needed; only the one-time user/API-key bootstrap above applies.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。