# vearch/vearch

Distributed vector search for AI-native applications

Repository: https://github.com/vearch/vearch
Canonical: https://ross.abutalabs.com/products/vearch
Homepage: https://vearch.github.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: vectors, vector-search, cloud-native, document-retrieval, embeddings, vector-database, hybrid-search, rag, retrieval-augmented-generation, ai-native, ai-native-database
Last push: 2026-07-27T05:29:53+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 94, release rhythm 57, longevity 100
- inputs: {"age_days": 2670, "days_push": 37, "days_rel": 210, "gap_med": 64.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2321, forks 365 (observed 2026-08-28T04:06:37.146219+00:00)

## What it is
Vearch is a cloud-native distributed vector database for efficient similarity search of embedding vectors, supporting hybrid vector and scalar filtering with replication and elastic scaling. It provides RESTful APIs and SDKs in Python, Go, Java, and Rust, and integrates with AI frameworks like LangChain and LlamaIndex.

## Use cases
- store and search embedding vectors for AI applications
- build a RAG knowledge base with a vector store backend
- hybrid search combining vector similarity with scalar filters
- index and search millions of images for visual search
- use a vector database as memory backend for LLM agents
- deploy a scalable self-hosted vector database on Kubernetes

## When to choose
- you need distributed, horizontally scalable vector search with replication
- you want hybrid vector plus scalar filtering in one database
- you need LangChain or LlamaIndex integration for RAG
- you want a self-hosted cloud-native vector database with Helm deployment

## When to avoid
- you only need a small in-process similarity search library without a server
- your stack requires a managed cloud vector database service
- you need full-text search as the primary workload rather than vector search

## Facets
- artifact type: service
- maturity: active
- function: vector-database, search-engine, database, rag
- domain: databases, machine-learning, artificial-intelligence
- platform: cloud, self-hosted, python, go, jvm, rust
- tags: vector-search, embeddings, hybrid-search, similarity-search, distributed-database, cloud-native, ai-native, document-retrieval, langchain, llamaindex, search, retrieval-augmented-generation, docker, kubernetes, linux

## Member repositories
- vearch/vearch (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.146219+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 2026-08-30T02:38:48.076449+00:00, confidence not recorded.
  - readme: https://github.com/vearch/vearch (fetched 2026-08-28T04:06:37.146219+00:00, sha b5d1807e7884)
  - homepage: https://vearch.github.io (fetched 2026-08-29T10:18:58.565389+00:00, sha eded2a84e630)
  - registry_pypi: https://pypi.org/pypi/vearch/json (fetched 2026-08-29T10:18:58.574260+00:00, sha 8a244fbd8581)
- Data as of 2026-08-30T08:39:29.467469+00:00.