---
title: "Open-source vector databases for RAG"
type: "category"
slug: "vector-databases"
canonical_url: "https://www.graphcanon.com/categories/vector-databases"
tool_count: 151
description: "Compare Qdrant, Chroma, Weaviate, and pgvector for RAG retrieval. GraphCanon ranks open-source vector databases by GitHub adoption and maintenance, not ads."
---

# Vector Databases

*GraphCanon updated Aug 22, 2026*

Vector databases store embeddings for similarity search, the retrieval layer behind most RAG stacks. Use a dedicated store when you need scale, hybrid search, or managed ops; pgvector or an in-memory index often wins below ~100k vectors. GraphCanon ranks tools by live GitHub stars and freshness, then links head-to-head compares and alternatives so you can pick on constraints, not hype. milvus currently leads this list at 45,402 GitHub stars among 151 published tools.

151 tools in this category (showing the top 60 by stars).

## Featured comparisons

- [Qdrant vs Chroma](/compare/chroma-core-chroma-vs-qdrant-qdrant.md)
- [Qdrant vs Weaviate](/compare/qdrant-qdrant-vs-weaviate-weaviate.md)
- [Qdrant vs pgvector](/compare/pgvector-pgvector-vs-qdrant-qdrant.md)

## Alternatives hubs

- [Qdrant alternatives](/tools/qdrant-qdrant/alternatives.md)
- [Chroma alternatives](/tools/chroma-core-chroma/alternatives.md)
- [Weaviate alternatives](/tools/weaviate-weaviate/alternatives.md)

## Stacks

- [The RAG stack](/stacks/rag-pipeline.md)

## Tools

- [milvus](/tools/milvus-io-milvus.md) - High-performance cloud-native vector database (★ 45,402) [Very active]
- [WeKnora](/tools/tencent-weknora.md) - Open-source LLM knowledge platform for creating a queryable RAG, autonomous reasoning agent, and self-maintaining Wiki. (★ 19,992) [Very active]
- [qdrant](/tools/qdrant-qdrant.md) - High-performance, massive-scale Vector Database and Vector Search Engine (★ 33,629) [Very active]
- [tidb](/tools/pingcap-tidb.md) - Scalable, cloud-native database with ACID transactions and vector search support. (★ 40,446) [Very active]
- [cognee](/tools/topoteretes-cognee.md) - Cognee is the open-source AI memory platform for agents. (★ 30,121) [Very active]
- [meilisearch](/tools/meilisearch-meilisearch.md) - A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. (★ 59,034) [Very active]
- [langchain4j](/tools/langchain4j-langchain4j.md) - Java library for building LLM-powered applications on the JVM (★ 12,813) [Very active]
- [llm-app](/tools/pathwaycom-llm-app.md) - Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. (★ 59,037) [Steady]
- [zvec](/tools/alibaba-zvec.md) - A lightweight, lightning-fast, in-process vector database (★ 15,455) [Very active]
- [mempalace](/tools/mempalace-mempalace.md) - The best-benchmarked open-source AI memory system. (★ 58,400) [Very active]
- [weaviate](/tools/weaviate-weaviate.md) - Open-source vector database for storing objects and vectors with structured filtering (★ 16,681) [Very active]
- [turbovec](/tools/ryancodrai-turbovec.md) - A vector index built on TurboQuant, written in Rust with Python bindings (★ 14,822) [Very active]
- [memvid](/tools/memvid-memvid.md) - Memory layer for AI Agents (★ 16,386) [Steady]
- [orama](/tools/oramasearch-orama.md) - A complete search engine and RAG pipeline with support for full-text, vector, and hybrid search. (★ 10,523) [Active]
- [redis](/tools/redis-redis.md) - Redis is a preferred cache, data structure server, and document & vector query engine for real-time applications. (★ 75,627) [Very active]
- [RuVector](/tools/ruvnet-ruvector.md) - High Performance Real-Time Self-Learning Ai Vector GNN Memory DB (★ 4,387) [Very active]
- [infinity](/tools/infiniflow-infinity.md) - AI-native database for LLM applications offering fast hybrid search capabilities. (★ 4,675) [Very active]
- [OpenMemory](/tools/caviraoss-openmemory.md) - Local persistent memory store for LLM applications (★ 4,457) [Very active]
- [claude-context](/tools/zilliztech-claude-context.md) - Code search MCP for Claude Code. Make entire codebase the context for any coding agent. (★ 12,408) [Steady]
- [chroma](/tools/chroma-core-chroma.md) - Search infrastructure for AI (★ 28,898) [Very active]
- [oceanbase](/tools/oceanbase-oceanbase.md) - The Fastest Distributed Database for Transactional, Analytical, and AI Workloads (★ 10,252) [Very active]
- [SocratiCode](/tools/giancarloerra-socraticode.md) - Enterprise-grade codebase intelligence with local setup, hybrid semantic search, and polyglot dependency graphs (★ 3,263) [Very active]
- [core](/tools/cheshire-cat-ai-core.md) - AI agent microservice (★ 3,081) [Active]
- [vespa](/tools/vespa-engine-vespa.md) - The AI search platform (★ 7,054) [Very active]
- [TencentDB-Agent-Memory](/tools/tencentcloud-tencentdb-agent-memory.md) - Fully local long-term memory for AI Agents via 4-tier pipeline (★ 9,234) [Very active]
- [bootcamp](/tools/milvus-io-bootcamp.md) - Dealing with all unstructured data including reverse image search, audio search, molecular search, video analysis, and question-answer systems. (★ 2,443) [Active]
- [fastembed](/tools/qdrant-fastembed.md) - Fast, Accurate, Lightweight Python library for creating state-of-the-art embeddings (★ 3,158) [Very active]
- [examples](/tools/pinecone-io-examples.md) - Jupyter Notebooks to help you get hands-on with Pinecone vector databases (★ 3,036) [Very active]
- [vearch](/tools/vearch-vearch.md) - Distributed vector search for AI-native applications (★ 2,320) [Active]
- [VCPToolBox](/tools/lioensky-vcptoolbox.md) - VCP acts as middleware between AI model APIs and frontend applications for AGI OS development. It enhances LLMs with statefulness, memory, tool invocation capabilities. (★ 2,257) [Very active]
- [dragonfly](/tools/dragonflydb-dragonfly.md) - A modern replacement for Redis and Memcached (★ 30,903) [Very active]
- [helix-db](/tools/helixdb-helix-db.md) - OLTP graph-vector database built in Rust on Object Storage (★ 5,797) [Very active]
- [JustHireMe](/tools/vasu-devs-justhireme.md) - Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials. (★ 2,233) [Active]
- [memsearch](/tools/zilliztech-memsearch.md) - A persistent, unified memory layer for all your AI agents backed by Markdown and Milvus. (★ 2,491) [Very active]
- [lancedb](/tools/lancedb-lancedb.md) - Developer-friendly OSS embedded retrieval library for multimodal AI. (★ 11,014) [Very active]
- [databend](/tools/databendlabs-databend.md) - All-in-One Data Warehouse: Analytics, Search, AI, and Python Sandboxing Reimagined From Scratch. (★ 9,420) [Very active]
- [EmbedAnything](/tools/starlightsearch-embedanything.md) - Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust (★ 1,304) [Active]
- [rag_api](/tools/danny-avila-rag-api.md) - ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector (★ 885) [Very active]
- [selfhost-ai](/tools/kossakovsky-selfhost-ai.md) - Self-hosted AI automation platform (★ 919) [Active]
- [SeekStorm](/tools/seekstorm-seekstorm.md) - Vector & Lexical Search Library and Multi-tenancy Server (★ 1,908) [Very active]
- [Agent_Memory_Techniques](/tools/nirdiamant-agent-memory-techniques.md) - Agent memory for LLMs: runnable Jupyter notebooks on various memory and knowledge techniques. (★ 924) [Very active]
- [OpenSwarm](/tools/unohee-openswarm.md) - Autonomous AI dev team orchestrator powered by Claude Code CLI. (★ 838) [Very active]
- [automem](/tools/verygoodplugins-automem.md) - Graph-vector memory service for durable, relational AI assistant memory (★ 802) [Active]
- [endee](/tools/endee-io-endee.md) - A high-performance vector database handling up to 1B vectors on one node (★ 1,305) [Active]
- [deeplake](/tools/activeloopai-deeplake.md) - AI Data Runtime for Agents with scalable retrieval and training features (★ 9,224) [Steady]
- [recipes](/tools/weaviate-recipes.md) - End-to-end notebooks for using Weaviate features and integrations. (★ 944) [Active]
- [paradedb](/tools/paradedb-paradedb.md) - One Postgres for your application data, full-text search, vector retrieval, and aggregations. (★ 9,117) [Very active]
- [NornicDB](/tools/orneryd-nornicdb.md) - Distributed Graph+Vector Database with Temporal MVCC and Low-Latency HNSW Search (★ 843) [Very active]
- [cuvs](/tools/nvidia-cuvs.md) - A library for vector search and clustering on the GPU (★ 821) [Very active]
- [Wax](/tools/christopherkarani-wax.md) - Single-file memory layer for AI agents with sub-millisecond RAG on Apple Silicon using Metal optimization (★ 786) [Very active]
- [VectorChord](/tools/supervc-stack-vectorchord.md) - Scalable, fast, and disk-friendly vector search in Postgres (★ 1,758) [Very active]
- [pgvector](/tools/pgvector-pgvector.md) - Open-source vector similarity search for Postgres (★ 22,375) [Very active]
- [grepai](/tools/yoanbernabeu-grepai.md) - Semantic Search & Call Graphs for AI Agents (100% Local) (★ 1,789) [Steady]
- [VectorDBBench](/tools/zilliztech-vectordbbench.md) - Benchmark for vector databases (★ 1,164) [Active]
- [faraday](/tools/infobyte-faraday.md) - Open Source Vulnerability Management Platform (★ 6,683) [Active]
- [qdrant-client](/tools/qdrant-qdrant-client.md) - Python client for Qdrant vector search engine (★ 1,346) [Very active]
- [MineContext](/tools/volcengine-minecontext.md) - Proactive context-aware AI partner (★ 5,476) [Slowing]
- [matrixone](/tools/matrixorigin-matrixone.md) - AI-native HTAP database with Git-for-Data and built-in vector search (★ 1,879) [Very active]
- [infinispan](/tools/infinispan-infinispan.md) - Highly scalable NoSQL cloud data store and in-memory cache platform (★ 1,345) [Very active]
- [RediSearch](/tools/redisearch-redisearch.md) - A query and indexing engine for Redis (★ 6,216) [Very active]

## Common questions

### What are the best vector databases tools?

GraphCanon ranks Vector Databases tools by GitHub adoption and freshness. milvus is the current leader (45,402 stars). See the full list on this page - sorted by stars, with [maintenance labels](/glossary/trust-and-signals/maintenance-label) and graph relationships.

### How does GraphCanon rank Vector Databases tools?

We sort by GitHub stars and push recency on category pages, not paid placement. Alternatives and compare pages use [typed graph edges](/glossary/knowledge-graph/typed-edge) (alternative, successor, integrates_with) plus shared categories - constraint-first, not marketing votes.

### How many tools are in Vector Databases?

151 published tools are tagged with Vector Databases in the GraphCanon knowledge graph.

### What are popular Vector Databases comparisons?

Head-to-head compare pages in this category include Qdrant vs Chroma, Qdrant vs Weaviate, Qdrant vs pgvector. Each comparison uses live GitHub stats and optional [trust signals](/glossary/trust-and-signals/trust-signal) - see the comparisons block on this page.

### Which stacks use Vector Databases?

Curated workflow pages that include Vector Databases: [The RAG stack](/stacks/rag-pipeline). Each stack step includes when-not-to-use guidance.

### Where are graph-backed alternatives hubs for Vector Databases?

High-intent OSS-vs-OSS alternatives pages include [Qdrant alternatives](/tools/qdrant-qdrant/alternatives), [Chroma alternatives](/tools/chroma-core-chroma/alternatives), [Weaviate alternatives](/tools/weaviate-weaviate/alternatives). Each hub ranks typed graph neighbors and constraint tags - not popularity votes.

### Is there a machine-readable Vector Databases list?

Yes. Append `.md` to this URL or fetch [`/md/categories/vector-databases`](/md/categories/vector-databases) for a markdown twin. The JSON API exposes the same corpus at [`/api/graphcanon/categories/vector-databases`](/api/graphcanon/categories/vector-databases).

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/categories/vector-databases`](/api/graphcanon/categories/vector-databases)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_