设计与开发：NIKHIL CHARY SRIRAMOJUGitHub ·LinkedIn

Groq驱动的ReAct代理覆盖你的日历、笔记和扫描图像，通过Model Context协议曝光。混合RAG（pgvector + tsvector + rrf）、CNN/OCR视觉工作器、Next.js带有3D上下文图的UI，全部在Docker Compose中实现。

两种逃跑方式

• 静态网站（GitHub Pages）: docs/ — 无构建，完全运行于浏览器（Groq BYOK，本地混合 RAG，浏览器内 CNN/OCR，Three.js 图表）。参见 [GITHUB_PAGES_GUIDE.md。
• 全栈（Docker）: TypeScript MCP 服务器 + Postgres/pgvector + Python CNN 工作器，见下文。

跑它

• 用户界面：http://localhost:3000 ·API：http://localhost:4000 ·MCP：http://localhost:4000/mcp
• 该模式在从 scripts/init_db.sql 开始的第一个 Postgres 自动应用。 手动重新应用：docker compose exec -T postgres psql -U mcp -d mcp < scripts/init_db.sql

试试看

CLI（无界面）：npm i && DATABASE_URL=postgresql://mcp:mcp@localhost:5432/mcp GROQ_API_KEY=... CNN_WORKER_URL=http://localhost:8000 npm run cli （运行docker compose up postgres cnn-worker以获取依赖关系）。

Personal MCP Assistant

Designed & developed by NIKHIL CHARY SRIRAMOJU · GitHub · LinkedIn

Groq-powered ReAct agent over your calendar, notes and scanned images, exposed through the Model Context Protocol. Hybrid RAG (pgvector + tsvector + RRF), CNN/OCR vision worker, Next.js UI with a 3D context graph, all in Docker Compose.

Two ways to run

• Static site (GitHub Pages): docs/ — no build, runs fully in the browser (Groq BYOK, local hybrid RAG, in-browser CNN/OCR, Three.js graph). See GITHUB_PAGES_GUIDE.md.
• Full stack (Docker): TypeScript MCP server + Postgres/pgvector + Python CNN worker, below.

Run it

cp .env.example .env        # set GROQ_API_KEY
docker compose up --build

• UI: http://localhost:3000 · API: http://localhost:4000 · MCP: http://localhost:4000/mcp
• The schema is applied automatically on first Postgres start from scripts/init_db.sql. Re-apply manually: docker compose exec -T postgres psql -U mcp -d mcp < scripts/init_db.sql

Test it

# health
curl localhost:4000/health
# add a note via the agent
curl -s localhost:4000/api/chat -H 'content-type: application/json' \
  -d '{"sessionId":"t1","message":"Create a note titled Sprint plan: finish API auth, review CNN worker. Tag it work."}'
# add an event, then ask for a prep summary
curl -s localhost:4000/api/chat -H 'content-type: application/json' \
  -d '{"sessionId":"t1","message":"Schedule Sprint review next Monday 3pm-4pm IST, then summarise prep from my notes."}'
# upload a whiteboard photo
curl -F [email protected] localhost:4000/api/upload

CLI (no UI): npm i && DATABASE_URL=postgresql://mcp:mcp@localhost:5432/mcp GROQ_API_KEY=... CNN_WORKER_URL=http://localhost:8000 npm run cli (run docker compose up postgres cnn-worker for the dependencies).

MCP Inspector / Claude Desktop: npx @modelcontextprotocol/inspector → Streamable HTTP → http://localhost:4000/mcp, or stdio via npm run mcp:stdio.

Layout

src/mcp tools (Zod) · src/agent Groq loop + reflection · src/rag embedder + RRF · src/cnn vision client · src/db pool · src/ui Next.js · docs/ static site · cnn-worker/ Python OCR/CNN · scripts/init_db.sql

Tools

get_events, create_event, reschedule_event, detect_schedule_conflicts, hybrid_search_notes, create_note, update_note, ingest_visual_document, store_agent_fact, retrieve_long_term_memory, reflect_and_validate, synthesize_cross_context_summary

Notes

• llama-3.3-70b-versatile by default; change GROQ_MODEL (e.g. a Llama 4 Scout id from Groq’s model list).
• Groq has no embeddings endpoint, so embeddings are local-hashed by default or via EMBEDDING_URL (1536 dims, OpenAI-compatible).
• First run: I couldn’t run npm install/Docker in my sandbox, so expect to fix a typing nit or two on first build. Send me the error and I’ll patch it.