# supavec/supavec

The open-source alternative to Carbon.ai. Build powerful RAG applications with any data source, at any scale.

Repository: https://github.com/supavec/supavec
Canonical: https://ross.abutalabs.com/products/supavec
Homepage: https://www.supavec.com
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: nextjs, rag, typescript, tailwindcss, ai
Last push: 2025-12-28T18:59:40+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 59, release rhythm 35, longevity 44
- inputs: {"age_days": 617, "days_push": 248, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1233, forks 113 (observed 2026-08-28T04:04:04.602814+00:00)

## What it is
Supavec is an open-source RAG-as-a-Service platform (an alternative to Carbon.ai) that lets developers upload documents, generate embeddings, and query them via a simple REST API with streaming chat responses. It is built with Next.js, Supabase, and Bun, supports multi-tenant isolation via row-level security, and can be self-hosted or used via its hosted cloud version.

## Use cases
- add document-based RAG search to my app via an API
- build a chatbot that answers questions from my own documents
- self-host a RAG pipeline for internal knowledge base Q&A
- embed and search PDFs, docs, and support tickets with citations
- build a customer support copilot over Zendesk/Notion/Confluence docs
- add an AI-powered search bar over my documentation site
- analyze sales call transcripts with AI and get cited answers

## When to choose
- you want a hosted-style RAG API you can also self-host with full source access
- you need multi-tenant document ingestion with team-level data isolation
- you want quick setup with REST endpoints for upload, embedding, search, and chat
- you need streaming chat responses and batch embedding to cut costs

## When to avoid
- you need a fully managed enterprise RAG platform with SLAs and on-prem support contracts
- you want a no-code tool rather than an API-first developer product
- you need heavy ETL over hundreds of exotic data source connectors out of the box
- you require non-Postgres vector stores or custom embedding pipelines

## Facets
- artifact type: service
- maturity: active
- function: rag, vector-database, search-engine, api-framework, llm-inference
- domain: large-language-models, artificial-intelligence, developer-tools, apis, self-hosted
- platform: self-hosted, bun, cloud
- tags: rag-as-a-service, embeddings-api, document-ingestion, multi-tenant, nextjs, supabase, open-source-alternative, carbon-ai-alternative, retrieval-augmented-generation, web-server, nodejs, docker

## Member repositories
- supavec/supavec (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:04.602814+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:22:18.103954+00:00, confidence not recorded.
  - readme: https://github.com/supavec/supavec (fetched 2026-08-28T04:04:04.602814+00:00, sha 49e46f2d5a82)
  - homepage: https://www.supavec.com (fetched 2026-08-29T12:21:53.125222+00:00, sha 3542073e13fa)
  - site_page: https://docs.supavec.com/ (fetched 2026-08-29T12:21:53.129721+00:00, sha fb93691ee316)
  - site_page: https://go.supavec.com/docs (fetched 2026-08-29T12:21:53.131342+00:00, sha 1b83f4202592)
  - site_page: https://www.supavec.com/pricing (fetched 2026-08-29T12:21:53.127871+00:00, sha 142195960fb7)
- Data as of 2026-08-30T08:39:29.467469+00:00.