AgentSidekick

Which vector databases are used for AI agents?

Short answer DER

As of 2026-11-21, the most-starred vector databases in AgentSidekick's curated records are Milvus (46,712 GitHub stars), Faiss (41,841) and Qdrant (35,652), ranked by GitHub stars of each project's own repository. We track 10 curated vector databases; 5 have MCP support recorded, and 2 had no star data at build time, so they are listed after.

AgentSidekick, as of ยท based on 10 products

The evidence

Vector databases for AI agents: 10 curated recordsCUR

Records researched by AgentSidekick against official sites, docs and repositories; stars and push dates are read from GitHub. "Not recorded" means we found no MCP support statement, not that it is absent.

Vector databases for AI agents: 10 curated records
#ProductTypePublisherLicenceOpen sourcePricing modelGitHub starsLast pushMCP support
1MilvusInfrastructureZilliz (LF AI & Data)Apache-2.0Yesopen-source46,7122026-11-21Yes (curated)
2FaissLibraryMetaMITYesopen-source41,8412026-11-20Not recorded
3QdrantInfrastructureqdrantApache-2.0Yesfreemium35,6522026-11-20Yes (curated)
4ChromaInfrastructureChromaApache-2.0Yesfreemium29,7212026-11-20Yes (curated)
5pgvectorInfrastructurepgvectorPostgreSQLYesopen-source23,7602026-11-21Not recorded
6WeaviateInfrastructureweaviateBSD-3-ClauseYesfreemium16,9592026-11-21Yes (curated)
7LanceDBInfrastructurelancedbApache-2.0Yesfreemium11,9602026-11-21Not recorded
8VespaInfrastructureVespa.aiApache-2.0Yesopen-source7,1892026-11-21Not recorded
9PineconeSaaS productPineconeUnknownNofreemiumUnknownUnknownYes (curated)
10turbopufferSaaS productturbopufferUnknownNousage-basedUnknownUnknownNot recorded

How the ranking was made. The list is ordered by GitHub stars of the product's own repository, highest first (a product inside a shared monorepo has no stars of its own and is listed after); products without star data follow, alphabetically. Only curated records in the "vector-databases" segment are included. GitHub stars measure popularity, not quality, security or fit for your use.

Limit. Pricing model is a category (open-source, freemium, paid, usage-based), not a price. AgentSidekick has not benchmarked or security-reviewed any of these products.

Which licences do they use? Apache-2.0 5, Unknown 2, MIT 1, PostgreSQL 1 and BSD-3-Clause 1.

Which are not open source? Pinecone and turbopuffer.

Which was updated most recently? Vespa, last pushed 2026-11-21.

How big is the wider category? The Vector Databases category holds 470 catalogue products, including uncurated ones (derived by keyword rules).

Sources

Pages the records behind this answer were taken from. Counts and rankings are computed by the site from these records.

How claims are labelled and ranked: claim kinds, ranking rules, compatibility statuses. Spotted an error? See corrections.

Page data last updated .