AI Support Chatbot adds an AI assistant to a website in minutes. You point it at your website or upload your documents, and it learns that content. Visitors then get answers based on what you've published — not generic guesses.
Every answer shows where it came from, so people can trust it.
- Grounded answers — responses are built from your content, with the sources listed.
- Learns from anything — website pages, PDFs, Word documents, or text files.
- Multiple sites — manage several websites and their knowledge from one dashboard.
- See the conversations — review what people ask and how the assistant is performing.
- Your choice of model — connect any model through OpenRouter.
- Add a website or upload documents.
- The app reads the content and builds a searchable knowledge base.
- Ask a question — the assistant finds the most relevant parts and answers with citations.
Docker is only needed to run this project on your own machine — for a demo or screenshots. It is not a deployment setup.
cp .env.example .env # add your OpenRouter API key
docker compose up --buildThen open http://localhost:3000. Add a site, let it finish indexing, and ask it something in the Playground.
FastAPI, PostgreSQL, and Next.js, with models served through OpenRouter.
MIT
