N0x – LLM inference, agents, RAG, Python exec in browser, no back end
Full ReAct agent loop running locally with WebGPU and Pyodide—no server required.
Open source AI customer support agent with RAG. Upload your docs, get a chat widget with citations. Built on OnCell.
One-file RAG chatbot backend when Chatbase and CustomGPT already dominate this space.
Small businesses and developers needing quick support bot setup
Chatbase · CustomGPT · Intercom Fin
Stack: Next.js + OnCell + OpenRouter.
Full ReAct agent loop running locally with WebGPU and Pyodide—no server required.
Single-file multi-agent workspace with MCP tools, WebGPU offline mode, full data sovereignty.
AI-powered backend-in-a-box, but Firebase, Supabase, and Parse already do this faster.
One-file backend is OnCell's flex, but functionally it's another Perplexity clone.
Another reactive JS library in a sea of Solid, Svelte, and Preact.
Client-side noise mapping when most tools require server infrastructure.