Open source vector-database projects

Every project in the registry tagged vector-database, ranked by real GitHub adoption.

projects 8 combined stars ★ 122K refresh nightly
01 llama_index ★ 52K

LlamaIndex is the document processing platform for AI

last push5 hours ago languagePython licenseMIT
02 PageIndex ★ 36K

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

last push8 hours ago languagePython licenseMIT
03 lancedb ★ 11K

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

last push5 hours ago languageRust licenseApache-2.0
04 Orama ★ 11K

Full-text & vector search at the edge.

last push7 days ago languageTypeScript license
05 genkit ★ 6.4K

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

last push6 hours ago languageTypeScript licenseApache-2.0
06 knowhere ★ 3.3K

Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

last push20 hours ago languagePython licenseApache-2.0
07 OpenContracts ★ 1.5K

The open document intelligence platform for builders and hackers - DMS for the agentic world

last push8 hours ago languagePython licenseMIT
08 automem ★ 813

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

last push7 days ago languagePython licenseMIT

Related tags

← all tags

Frequently asked questions

How many open source vector-database projects are there?

This registry tracks 8 projects tagged vector-database, with 121,967 GitHub stars between them. The most-adopted is llama_index at 52,202 stars.

Are these vector-database projects free to use?

Yes — 7 of the 8 carry an explicit open-source licence across 2 distinct licences, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.

Which vector-database project should I choose?

The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.

Are these vector-database projects still maintained?

8 of the 8 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.