Forgekit: An Open-Source Next.js AI Starter Kit with RAG and pgvector

Description and use

Forgekit is a ready-to-run Next.js 16 starter kit for AI chat apps featuring streaming, multi‑provider models, authentication, rate limiting, RAG with pgvector, and Docker deployment.

Problem

Developers need a ready-to-run AI application template that handles streaming chat, authentication, rate limiting, document retrieval, and deployment without assembling multiple libraries.

Outcome

Forgekit delivers a turnkey AI chat application with streaming, multi-provider model support, built-in tools, RAG via pgvector, per-user rate limiting, and a Docker image ready for deployment.

Workflow

• Clone the repo: git clone https://github.com/fabwaseem/forgekit.git
• Navigate into the repo: cd forgekit
• Run the setup script: bash scripts/setup.sh
• Start the development server: pnpm dev
• Open http://localhost:3000, create an account, and configure at least one model provider in .env

Evidence

Clone it, run one setup script, and you have a working AI chat app on your own machine.

Source

To run Forgekit locally, install Node.js 22, pnpm and Docker, then clone the repo and run the setup script.

Source

The model picker only lists providers you have configured, so you never see a model that would fail.

Source