AI Embeddings, pgvector & AI Coding Playground

This playground runs AI models, Python, and PostgreSQL entirely in your browser. No data leaves your machine.

Requirements:

Local AI (WebLLM): Chrome/Edge with WebGPU support. Downloads a ~1-2GB model on first use. Needs a GPU with 4GB+ VRAM.
API mode: Any modern browser. Bring your own API key (OpenAI, Anthropic, or OpenRouter). Keys are stored only in your browser's localStorage.
Embeddings: Run locally via Transformers.js (~30MB model download). No API key needed.
Storage: PostgreSQL 16 + pgvector runs in-browser via PGlite WASM.

AI-assisted coding editor + vector embeddings + PostgreSQL with pgvector. Everything runs in your browser.

AI Provider:

WebLLM

Local, no API key

Waiting for setup...

AI Assistant Ask it to write embedding code, SQL queries, or data analysis

I'm your AI coding assistant. I can write Python code that uses pgvector for semantic search, embeddings, and PostgreSQL queries. Try asking me to: "Build a FAQ bot that finds the most relevant answer to a question" or "Create a movie recommender" — or click a Quick Action below. If code has errors, click "Ask AI to fix" and I'll debug it for you.

Python + SQL Editor

Results

Results will appear here after running code or SQL.

Direct SQL

Quick Actions