# Best vector search and retrieval databases for AI agents (slim)

> Meilisearch (A), Pinecone API + MCP (BB) and Supabase API + MCP (BB) lead the 14 ranked vector search and retrieval databases. Picks by need, strengths, weaknesses and prices from the Anchor benchmark.

- Full: https://www.anchorterminal.com/best/vector-search/index.md (~5,800 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/best/vector-search/index.json · canonical https://www.anchorterminal.com/best/vector-search/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

The 10 highest-scoring of 14 vector search and retrieval databases on the Anchor benchmark, with a pick for each need and where each one falls short. Scores come from public evidence, re-checked as vendors change.

- Ranked: 14 · agent-ready (BB or better): 6 · accept x402: 0 · hosted endpoints: 8
- Full ranked table: https://www.anchorterminal.com/categories/vector-search.md
- Head-to-head comparisons: https://www.anchorterminal.com/compare/vector-search/index.md (85)
- Methodology: https://www.anchorterminal.com/benchmark/index.md

## The shortlist

| # | Tool | Grade | Score | Best for | Price | Where |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [Meilisearch](https://www.anchorterminal.com/tools/meilisearch.md) | A | 78.6 | Retrieval where typo-tolerant keyword relevance, filters and facets matter as much as vectors, with embeddings generated by the engine. | $30 / mo | local |
| 2 | [Pinecone API + MCP](https://www.anchorterminal.com/tools/pinecone.md) | BB | 76.2 | Teams that want a hosted index with nothing to run, hosted embedding and reranking, and a versioned API agents can rely on. | $20 / mo | hosted and local |
| 3 | [Supabase API + MCP](https://www.anchorterminal.com/tools/supabase-mcp.md) | BB | 75.6 | Agents building on or administering Supabase projects, and for retrieval that wants vectors, full-text and SQL filters in one database. | $25 / mo | hosted and local |
| 4 | [Qdrant API + MCP](https://www.anchorterminal.com/tools/qdrant.md) | BB | 75.3 | Filtered vector search and multi-tenant retrieval where the agent can call REST, and for teams that want the same engine self-hosted and managed. | Freemium | hosted and local |
| 5 | [Typesense API + MCP](https://www.anchorterminal.com/tools/typesense.md) | BB | 70.7 | Retrieval where keyword relevance, typo tolerance, filters and facets matter as much as vectors, and for teams that want a hosted MCP server with tight permissions. | $0.09 / GB | hosted |
| 6 | [Vespa](https://www.anchorterminal.com/tools/vespa.md) | BB | 70 | Teams that need hybrid retrieval with custom ranking at scale and can maintain a schema and application package. | $0.05 / vCPU-hr | local |
| 7 | [OpenSearch](https://www.anchorterminal.com/tools/opensearch.md) | B | 68 | A team that already runs OpenSearch for logs or text search and wants vectors and hybrid search in the same cluster, with fine-grained access control. | Free · OSS | local |
| 8 | [Weaviate API + MCP](https://www.anchorterminal.com/tools/weaviate.md) | B | 67.9 | Hybrid keyword and vector retrieval with filters and multi-tenancy, self-hosted or managed, and for agents that work over MCP. | $45 / mo | local |
| 9 | [Elasticsearch](https://www.anchorterminal.com/tools/elasticsearch.md) | B | 67.7 | Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security. | $0.09 / unit | local |
| 10 | [LanceDB](https://www.anchorterminal.com/tools/lancedb.md) | B | 65.4 | Agents whose code can import a library and keep retrieval data in object storage, from notebooks to multimodal datasets. | Freemium | local |

## Picks by need

- Highest score overall: [Meilisearch](https://www.anchorterminal.com/tools/meilisearch.md), A, 78.6/100 on the benchmark. Also [Pinecone API + MCP](https://www.anchorterminal.com/tools/pinecone.md), BB, 76.2/100.
- Schema & documentation: [Pinecone API + MCP](https://www.anchorterminal.com/tools/pinecone.md), 94/100 on schema & documentation, against 93 for the overall leader.
- Agent ergonomics: [Pinecone API + MCP](https://www.anchorterminal.com/tools/pinecone.md), 93/100 on agent ergonomics, against 87 for the overall leader.
- Security & auth: [Supabase API + MCP](https://www.anchorterminal.com/tools/supabase-mcp.md), 84/100 on security & auth, against 67 for the overall leader.
- Transparency & trust: [Supabase API + MCP](https://www.anchorterminal.com/tools/supabase-mcp.md), 90/100 on transparency & trust, against 74 for the overall leader.
- Lowest paid price per GB: [Milvus and Zilliz Cloud API + MCP](https://www.anchorterminal.com/tools/milvus-zilliz.md), $0.025 per GB, the lowest of the 10 listings here with a paid price in this unit (free allowances aside). Also [Weaviate API + MCP](https://www.anchorterminal.com/tools/weaviate.md), $0.029 per GB.
- A hosted MCP endpoint: [Pinecone API + MCP](https://www.anchorterminal.com/tools/pinecone.md), remote MCP server, nothing to install.
- The review panel's favourite: [Qdrant API + MCP](https://www.anchorterminal.com/tools/qdrant.md), 3.6/5 from 8 panel reviews.

## How to choose

- Hosted and self-hosted costs: Compare hosted and self-hosted costs at the same corpus size and vector dimension, since a unit price means little until stored and query volumes are fixed.
- Update delay before searchable: Check how long after a write an update becomes searchable, because an agent that stores a fact and immediately queries for it will miss the fact if indexing lags.
- Filter order and result counts: Check whether metadata filters are applied before or after ranking, since post-filtering can return fewer results than requested and silently weaken retrieval accuracy.
- Retrieval accuracy on your corpus: Check whether retrieval accuracy was measured on your own corpus and queries, since a score on another corpus says little about how well results will rank for your agent.

- How the benchmark tests this category: The same corpus indexed and the same queries run on every database. We measure retrieval accuracy, filter behaviour, update delay, p95 latency, setup effort and cost at a stated corpus size, and report hosted services and self-hosted deployments separately.

Each listing's verdict, strengths and weaknesses: https://www.anchorterminal.com/best/vector-search/index.md