Category · Developer & infrastructure
Vector search and retrieval databases for AI agents
Databases an agent can query for retrieval, with vector, keyword and hybrid search. Compared on retrieval accuracy, filters, how fast an update becomes searchable, p95 latency, setup effort and cost at a stated corpus size, with hosted and self-hosted costs reported apart.
Best vector search and retrieval databases for AI agents, the shortlist103 head-to-head comparisons
Capability keys db.vector · db.hybrid · db.fulltext · db.filters · db.serverless · All tools
letme.dev/db.vector picks the top-graded tool in this list and says how to call it direct (how letme works).
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/search
Filters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 35 | Pinecone API + MCPPinecone · HTTP API | Retrieval | A | 79.3 | 3.5 (8) | n/a | n/a | $20 / mo | API key | Hosted and local | ||
|
Managed, closed-source vector database with serverless indexes. Top strength OpenAPI files per API version, quarterly versions with at least 12 months of support each Top weakness Serverless reads in AWS us-west-2 returned 5xx errors for 11 hours on 17 September 2026 |
||||||||||||
| 52 | MeilisearchMeilisearch · HTTP API | Retrieval | A | 78.3 | 3.5 (4) | n/a | n/a | $30 / mo | API key | Local | ||
|
Open-source search engine from Meili SAS in Paris with typo-tolerant keyword search, vector and hybrid search, filters and facets. It runs self-hosted or as Meilisearch Cloud, with a REST API, SDKs and an experimental built-in MCP route. Top strength Keyword, vector and hybrid search in one request, with Top weakness The |
||||||||||||
| 89 | Typesense API + MCPTypesense · HTTP API | Retrieval | BB | 76.6 | 3.0 (2) | n/a | n/a | $0.09 / GB | OAuth or key | Hosted | ||
|
Open-source (GPL-3.0) search engine with typo-tolerant keyword search, vector and hybrid search, filters, facets, geo search, JOINs and built-in embedding. Top strength Keyword, vector and hybrid search with filters, facets, sorting and geo in one request Top weakness Server v30.2 from April 2026 is still the newest stable release |
||||||||||||
| 92 | Cloudflare AI SearchCloudflare · HTTP API | Retrieval | BB | 76.5 | 3.5 (4) | n/a | n/a | $0.75 / 1k req | OAuth or key | Local | ||
|
Cloudflare's managed retrieval service, formerly AutoRAG, indexes websites, R2 buckets and uploaded files and answers natural-language queries with vector, keyword or hybrid search, through a REST API, a Workers binding or a per-instance MCP endpoint. Top strength Hybrid vector and BM25 search on by default, with metadata filters applied before retrieval Top weakness Public endpoints, including MCP, answer anyone with the URL unless a custom domain sits behind Cloudflare Access |
||||||||||||
| 99 | Supabase API + MCPSupabase · HTTP API | Databases | BB | 76.2 | 3.3 (8) | n/a | n/a | $25 / mo | OAuth or key | Hosted and local | ||
|
Hosted Postgres with an auto-generated REST API (PostgREST), GraphQL, auth, storage, realtime and Edge Functions, plus a Management API and an official MCP server. Top strength OAuth 2.1 with dynamic client registration, plus personal access tokens scoped to chosen projects and permissions Top weakness The status feed lists 3 critical and 6 major platform incidents between 31 August and 31 October 2026, three of the majors on 21 and 22 October |
||||||||||||
| 214 | VespaVespa.ai AS · HTTP API | Retrieval | BB | 72.5 | 3.0 (4) | n/a | n/a | $0.05 / vCPU-hr | OAuth or key | Local | ||
|
Vespa is an open-source search engine from Vespa.ai AS for vector, text and hybrid retrieval with ranking, run self-hosted or on Vespa Cloud. Agents reach it through HTTP query and document APIs, the Vespa CLI and a Python client. Top strength Data-plane clients use mTLS certificates or tokens, each limited to Top weakness No OpenAPI file was found in the docs index. The APIs are described in reference pages only |
||||||||||||
| 229 | Qdrant API + MCPQdrant · HTTP API | Retrieval | BB | 72.2 | 3.6 (8) | n/a | n/a | Freemium | API key | Hosted and local | ||
|
Open-source vector database written in Rust, run yourself or on Qdrant Cloud. Top strength Database keys can be read-only, limited to chosen collections and expire after 90 days by default Top weakness The MCP server has 2 tools, can't manage collections, and last released on 10 December 2025 |
||||||||||||
| 272 | OpenSearchOpenSearch Software Foundation · HTTP API | Retrieval | BB | 71.1 | 3.8 (4) | n/a | n/a | Free · OSS | OAuth or key | Local | ||
|
OpenSearch is an open-source search and analytics engine with vector, text and hybrid search, run by its owner. Agents reach it through a REST API, official clients, an OpenSearch MCP Server and an MCP endpoint inside the cluster. Top strength Apache-2.0 for the engine, the plugins, the clients and the MCP server, under a foundation hosted by The Linux Foundation Top weakness No hosted service from the foundation. The owner installs, secures and runs the cluster, and no status page or SLA exists for the software |
||||||||||||
| 469 | Upstash Vector API + MCPUpstash · HTTP API | Retrieval | B | 66.5 | 3.0 (2) | n/a | n/a | $0.004 / 1k req | OAuth or key | Hosted | ||
|
Serverless vector database billed per request. Top strength $0.40 per 100,000 requests and a free plan with 10,000 queries and updates a day Top weakness The Vector changelog's last entry is August 2025 and the Python client last shipped in February 2025 |
||||||||||||
| 480 | LanceDBLanceDB · SDK + MCP | Retrieval | B | 66.3 | 3.0 (2) | n/a | n/a | Freemium | None | Local | ||
|
Open-source embedded database on the Lance columnar format. Top strength Embedded, no server, and tables can live directly in S3, GCS or Azure storage Top weakness No self-serve hosted API. Enterprise is sold through a contact form |
||||||||||||
| 588 | Milvus and Zilliz Cloud API + MCPZilliz · HTTP API | Retrieval | B | 64.1 | 3.5 (2) | n/a | n/a | $0. / unit | API key | Hosted and local | ||
|
Milvus is the open-source (Apache-2.0, LF AI and Data) vector database, run embedded as Milvus Lite, standalone or distributed on Kubernetes. Top strength Apache-2.0 under the LF AI and Data Foundation, run embedded as Milvus Lite, standalone or distributed Top weakness The Zilliz MCP server is still at 1.0.0 with no release carrying its August 2026 fix for token forwarding |
||||||||||||
| 775 | ElasticsearchElastic · HTTP API | Retrieval | C | 60 | 3.3 (4) | n/a | n/a | $0.09 / unit | OAuth or key | Local | ||
|
Elasticsearch is Elastic's search engine and vector database, with keyword, vector and hybrid search over a REST API. Agents reach it through that API or the Agent Builder MCP server on Elastic Cloud and Elastic Stack 9.2 or later. Top strength OpenAPI 3.0.3 file for the Serverless API with 311 operations, plus llms.txt and a Markdown twin of every docs page Top weakness 35 security advisories for Elasticsearch from 13 August to 6 October 2026, four of them High, all fixed in patch releases |
||||||||||||
| 781 | Weaviate API + MCPWeaviate · HTTP API | Retrieval | C | 59.9 | 3.5 (2) | n/a | n/a | $45 / mo | API key | Local | ||
|
Open-source vector database written in Go, run yourself or on Weaviate Cloud. Top strength Built-in MCP server with 4 typed tools, readOnly, destructive and idempotent hints on each, and documented error answers Top weakness No public status page or incident history |
||||||||||||
| 1136 | Chroma API + MCPChroma · HTTP API | Retrieval | D | 50.1 | 3.0 (2) | n/a | n/a | $250 / mo | API key | Hosted and local | ||
|
Open-source retrieval database that runs in-process, as a local server or as Chroma Cloud, a serverless hosted service. Top strength Runs in-process, as a local server or serverless on Chroma Cloud with the same v2 API Top weakness Six advisories against chromadb, two Critical and four High, have no patched release as of 5 November 2026 |
||||||||||||
| 1351 | Epsilla Vector DatabaseEpsilla · HTTP API | Retrieval | E | 40.4 | 1.5 (2) | n/a | n/a | $29 / mo | API key | Hosted | ||
|
Open-source (GPL-3.0) vector database with dense and sparse vectors, built-in embedding, filters and hybrid search through client-side retrievers and an RRF reranker. Top strength GPL-3.0 server you can run from one Docker image Top weakness No tagged release since 29 November 2025 and no release notes since March 2025 |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
Indexed, not reviewed (4)
Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.
| Listing | Kind | What it does | Why it's here |
|---|---|---|---|
| ArcadeDB MCP Server arcadedb.com | MCP server | Built-in MCP server for ArcadeDB multi-model database (graph, document, vector, time-series) | vendor's own, widely used |
| Brilliant brilliant.design | MCP server | Your coding agent designs with you on a real vector canvas: UIs, pages, components, export. | vendor's own |
| deepcontext wild-card.ai | MCP server | Advanced codebase indexing and semantic search MCP server | vendor's own |
| Picsha AI picsha.ai | MCP server | AI-native digital asset management: semantic search, generative image edits, and CDN delivery. | vendor's own |
How we test 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.
How the ranking works
Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.