What is Supavec used for?

Supavec is an open-source RAG-as-a-service platform that provides vector search and a chat API over your own data, positioned as an alternative to Carbon.ai. It is a good fit for adding document question answering to an app and building RAG features without managing vector infrastructure.

Is Supavec open source?

Yes. Supavec is open source under the Apache-2.0 licence. Its source code is on GitHub at supavec/supavec and is written mainly in TypeScript.

Yes. Supavec is open source, so the software itself is free to use. A managed cloud version is also available.

Can I self-host Supavec?

Yes. Supavec can be self-hosted on your own server or infrastructure.

What is Supavec an alternative to?

Supavec is an open-source alternative to Vectara. Other open-source alternatives to Vectara include RAGFlow, Trieve and Vespa.

Is Supavec actively maintained?

The most recent commit to Supavec was on 28 December 2025. The project has 1.2k stars on GitHub.

Supavec: open-source alternative to Vectara

About Supavec

Supavec is an open-source retrieval-augmented generation (RAG) service. It lets developers build AI applications that answer questions over their own documents by providing vector search and a chat API, without assembling the embedding and retrieval pipeline themselves. The project presents itself as an open-source alternative to Carbon.ai and offers both a cloud version and code you can run on your own infrastructure.

The README describes a multi-tenant design that uses row-level security for team-level data isolation, usage-based billing on the cloud version, and batched embeddings to reduce OpenAI costs. Retrieval can be tuned with configurable chunk size and overlap, and searches combine a file filter with cosine similarity. Operationally it includes PostHog analytics, request-level tracing with unique IDs, asynchronous usage logging, streaming or standard responses, and Redis-backed rate limiting.

The product is API-first with REST endpoints, documentation at docs.supavec.com and a related Python API repository. A chat interface shows live embedding previews for debugging. It is built with Next.js, Supabase, Tailwind CSS, Bun and Upstash, written in TypeScript, and licensed under Apache-2.0.

Key features

Vector search and chat API over your documents
Multi-tenant isolation with row-level security
Configurable chunk size and overlap
Streaming or standard API responses
Request tracing and PostHog analytics
Redis-backed rate limiting

Good fit for

→Adding document question answering to an app
→Building RAG features without managing vector infrastructure

Built with: TypeScript; Next.js; Tailwind CSS
Tags: rag; vector-search; embeddings; ai; api; nextjs; supabase; llm

Supavec: questions and answers

What is Supavec used for?: Supavec is an open-source RAG-as-a-service platform that provides vector search and a chat API over your own data, positioned as an alternative to Carbon.ai. It is a good fit for adding document question answering to an app and building RAG features without managing vector infrastructure.
Is Supavec open source?: Yes. Supavec is open source under the Apache-2.0 licence. Its source code is on GitHub at supavec/supavec and is written mainly in TypeScript.
Is Supavec free?: Yes. Supavec is open source, so the software itself is free to use. A managed cloud version is also available.
Can I self-host Supavec?: Yes. Supavec can be self-hosted on your own server or infrastructure.
What is Supavec an alternative to?: Supavec is an open-source alternative to Vectara. Other open-source alternatives to Vectara include RAGFlow, Trieve and Vespa.
Is Supavec actively maintained?: The most recent commit to Supavec was on 28 December 2025. The project has 1.2k stars on GitHub.