Show HN: ChatRAG – Next.js and AI SDK starter to ship RAG chatbots faster

I built the tech stack behind ChatRAG to handle the increasing number of clients I started getting about a year ago who needed Retrieval Augmented Generation (RAG) powered chatbots.

After a lot of trial and error, I settled on this tech stack for ChatRAG:

Frontend

- Next.js 16 (App Router) Latest React framework with server components and streaming

- React 19 + React Compiler: Automatic memoization, no more useMemo/useCallback hell

- Zustand: Lightweight state management (3kb vs Redux bloat)

- Tailwind CSS + Framer Motion: Styling + buttery animations

- Embed a chat widget version of your RAG chatbot on any web page, apart from creating a ChatGPT or Claude looking web UI

AI / LLM Layer

- Vercel AI SDK 5 – Unified streaming interface for all providers

- OpenRouter – Single API for Claude, GPT-4, DeepSeek, Gemini, etc.

- MCP (Model Context Protocol) – Tool use and function calling across models

RAG Pipeline

- Text chunking → documents split for optimal retrieval

- OpenAI embeddings (1536 dim vectors) – Semantic search representation

- pgvector with HNSW indexes – Fast approximate nearest neighbor search directly in Postgres

Database & Auth

- Supabase (PostgreSQL) – Database, auth, realtime, storage in one

- GitHub & Google OAuth via Supabase – Third party sign in providers managed by Supabase

- Row Level Security – Multi-tenant data isolation at the DB level

Multi-Modal Generation

- Use Fal.ai or Replicate.ai API keys for generating image, video and 3D assets inside of your RAG chatbot

Integrations

- WhatsApp via Baileys – Chat with your RAG from WhatsApp

- Stripe / Polar – Payments and subscriptions

Infra

- Fly.io / Koyeb – Edge deployment for WhatsApp workers

- Vercel – Frontend hosting with edge functions

My special sauce: pgvector HNSW indexes (m=64, ef_construction=200) give you sub-100ms semantic search without leaving Postgres. No Pinecone/Weaviate vendor lock-in.

Single-tenant vs Multi-tenant RAG setups: Why not both?

ChatRAG supports both deployment modes depending on your use case:

Single-tenant

- One knowledge base → many users

- Ideal for celebrity/expert AI clones or brand-specific agents

- e.g., "Tony Robbins AI chatbot" or "Deepak Chopra AI"

- All users interact with the same dataset and the same personality layer

Multi-tenant

- Users have workspace/project isolation — each with its own knowledge base, project-based system prompt and settings

- Perfect for SaaS products or platform builders that want to offer AI chatbots to their customers

- Every customer gets private data and their own RAG

This flexibility makes ChatRAG usable not just for AI creators building their own assistant, but also for founders building an AI SaaS that scales across customers, and freelancers/agencies who need to deliver production ready chatbots to clients without starting from zero.

After building multiple RAG powered chatbots that performed well and passed some accuracy tests, I packaged this stack into ChatRAG so developers can ship high quality RAG chatbots faster, whether it's for a personal AI assistant, a multi-tenant SaaS platform, or client projects.

My long term vision is to keep evolving ChatRAG so I can eventually release a fully open source version for everyone to build with.