Vector Search
Business capabilities this tag reaches
Information Technology Management 1
Variants seen in the corpus:
Vector DatabaseVector DatabasesVector Search
Providers using this tag (57)
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 1 Complete, well-documented, and agent-ready
Developing 19 Usable, with meaningful gaps to close
Thin 18 Limited public surface area
Emerging 10 Early or largely undocumented
Minimal 2 Almost no public developer surface
APIs with this tag (27)
Ranked by the provider's API Evangelist rating — the Kin Score is scored per provider, not per API, so every API of a provider shares its band. How the rating works →
Strong 6 Solid coverage with minor gaps
Seekr Vector database APIThe Vector database API from Seekr — 11 operation(s) for vector database.TiDB MCP ServerOfficial Model Context Protocol server maintained by PingCAP that exposes a TiDB or TiDB Cloud database to ...Vector Search Endpoints APIManage vector search endpoints for hosting vector search indexes.Vector Search Indexes APIManage vector search indexes for similarity search and retrieval-augmented generation workloads.Databricks Vector Search Endpoints APIThe Databricks Vector Search Endpoints API allows you to create, list, get, and delete vector search endpoi...Databricks Vector Search Indexes APIThe Databricks Vector Search Indexes API allows you to create, manage, query, and delete vector search inde...
Developing 11 Usable, with meaningful gaps to close
BuiltWith Vector Search APIText-based technology searches using vector embeddings for semantic similarity matching.Chroma JavaScript ClientThe Chroma JavaScript and TypeScript Client is a first-party SDK for interacting with Chroma from JavaScrip...Chroma Python ClientThe Chroma Python Client is a first-party SDK for interacting with both self-hosted Chroma servers and Chro...Sanity Embeddings Index APIThe Sanity Embeddings Index API enables creating and managing vector embedding indexes for Content Lake doc...Collate Vector Search APIAPIs for vector-based semantic search.Mistral Embeddings APIGenerate vector embeddings for text and code for retrieval, clustering, classification, and semantic search.Oracle APEX Generative AI APIAPIs for integrating generative AI capabilities into APEX applications, including chat, text generation, an...ScyllaDB Vector Search APIThe Vector Search API from ScyllaDB — 1 operation(s) for vector search.Kinetica Database REST APIPOST-only JSON REST API exposed by every Kinetica deployment on port 9191. Endpoints cover SQL execution (/...Kinetica Toolbelt MCP ServerHosted Model Context Protocol server that gives any MCP-speaking agent a single endpoint onto a Kinetica da...OpenMetadata Vector Search APIAPIs for vector-based semantic search.
Thin 7 Limited public surface area
Cohere Embed APIThe Cohere Embed API generates vector embeddings from text and images, enabling semantic search, clustering...Nhost AI APIAI toolkit providing GraphQL-based assistant management, auto-embeddings, session handling, and file stores...OpenSearch Search and Indexing REST APIThe core OpenSearch REST API for indexing documents, performing search queries (full text, vector, hybrid),...Upstash Developer APIManagement API for creating and administering Upstash Redis, Kafka, and Vector databases, teams, and accoun...Nomic Atlas APIREST API for the Nomic Atlas platform. Exposes endpoints for creating and managing datasets, building 2D se...OpenLLMetry Vector Database InstrumentationsInstrumentations for vector databases used in retrieval-augmented generation pipelines — Chroma, Pinecone, ...Apache LuceneLucene provides a comprehensive Java API for full-text indexing, searching, faceting, hit highlighting, spa...
Emerging 3 Early or largely undocumented
MilvusMilvus is an open source vector database built for scalable similarity search, supporting embedding-based A...KAITO RAGEngine APIRAGEngine exposes endpoints for managing retrieval-augmented generation services with embedded vector datab...Transwarp Hippo RESTful APIREST interface of the Transwarp Hippo distributed vector database. The published reference covers database ...
Companies reaching this through an API (14)
These companies publish an API, specification or operation carrying “Vector Search” but do not classify their business under it. Listed unranked and kept out of the count above, because one tagged operation is not a statement about what a company does.
Azure Databricks
BuiltWith
Collate
KAITO
LF AI and Data
Mistral AI
Nhost
Nomic AI
OpenLLMetry
OpenMetadata
OpenSearch
Oracle APEX
Sanity
Seekr
Score breakdown
Frequency
52.4
log-scaled weighted occurrences
Breadth
1.3
spread across providers
Quality lift
40.6
mean composite of providers using it
Cohesion
22.0
strength of nearest seed neighbor
Where this tag sits
Related tags
RAG 29 co-occurrences
Semantic Search 12 co-occurrences
Embeddings 22 co-occurrences
Retrieval 10 co-occurrences
Database 28 co-occurrences
Full-Text Search 7 co-occurrences
NoSQL 8 co-occurrences
Cluster 16 co-occurrences
Where this tag comes from
Provider tag60
Api tag28
Openapi tag3
Openapi op tag7
Markets provisional
Kin Score markets whose measured providers carry this tag. Share is the fraction of the market's measured providers that carry it — it describes the market, not this tag.
| Market | Share of the market's providers |
|---|---|
| Retrieval, Vector and RAG | 24% |
| Search API (Elasticsearch / OpenSearch shape) | 20% |
Cohort brief
Auto-generatedThe 57 providers in the APIs.io catalog tagged Vector Search, scored on the Kin Score. Every figure below is computed from the catalog — nothing here is written.
Providers
57
all scored
Mean Kin Score
38.7
+16.5 vs catalog 22.2
Mean Agent Readiness
21.9
+9.9 vs catalog 12
Spread
9.1–76.9
median 39.2 · σ 14.7
How the 57 split by band
Exemplar 1Strong 7Developing 19Thin 18Emerging 10Minimal 2
Facet averages, against the whole catalog
| Facet | This cohort | Catalog | Difference | Scored |
|---|---|---|---|---|
| Developer Ergonomics | 45.7 | 23.2 | +22.5 | 57 |
| Contract Quality | 35.9 | 17.2 | +18.7 | 57 |
| Operational Transparency | 28 | 13 | +15 | 57 |
| Access Clarity | 36.1 | 23.9 | +12.2 | 57 |
| Discoverability | 67 | 57.9 | +9.1 | 57 |
| Contract Governance | 9.4 | 6.5 | +2.9 | 57 |
A facet is averaged over the members that carry it, not over the whole cohort — the “Scored” column is that count. Averaging an absent facet as zero would score our own coverage gaps as the providers’ posture.
What this cohort publishes
| Artifact | This cohort | Catalog | Difference |
|---|---|---|---|
| MCP server (any) | 35% | 13% | +22 |
| MCP server (first-party) | 33% | 12% | +21 |
| Agent Skills | 0% | 0% | 0 |
| OAuth scopes | 12% | 11% | +1 |
| Security | 95% | 98% | -3 |
| Arazzo workflows | 4% | 2% | +2 |
| Governance rules | 28% | 16% | +12 |
mcp_pct counts any mcp/ artifact including ones API Evangelist derived from the provider OpenAPI; mcp_first_party_pct counts only servers the provider publishes. Prefer the latter.
Top by Kin Score
- 1 Elastic Stack 76.9
- 2 Couchbase 64.4
- 3 Timescale 63.9
- 4 PingCAP 61.4
- 5 Pinecone 59.2
- 6 Databricks 57.1
- 7 TileDB 55.1
- 8 Airweave 54.6
- 9 Mixedbread 53.1
- 10 DataStax 52.8
Top by Agent Readiness
- 1 Airweave 60.6
- 2 Databricks 58.3
- 3 Mixedbread 51.2
- 4 Typesense 45.8
- 5 Elastic Stack 43.9
- 6 Pinecone 42
- 7 Upstash 41.8
- 8 PingCAP 41.3
- 9 Ondemand 39.3
- 10 TileDB 35.5
All 57 members of this roster resolve to a scored provider in
the catalog.
Coverage caveat. 44 of 57 scored members had under half their catalog-attributable points satisfied at all (catalog_earned / catalog_max < 0.5). They are INCLUDED in the mean above. A large share here means the cohort mean is partly a measurement of how far our enrichment reached, not only of how these providers publish.Generated from the catalog build of 24 October 2026, across 31984 providers, using the same computation served by the APIs.io cohort API. Briefs are published for rosters of 5 or more scored providers; below that a distribution is not meaningful.
Coverage caveat. 44 of 57 scored members had under half their catalog-attributable points satisfied at all (catalog_earned / catalog_max < 0.5). They are INCLUDED in the mean above. A large share here means the cohort mean is partly a measurement of how far our enrichment reached, not only of how these providers publish.Generated from the catalog build of 24 October 2026, across 31984 providers, using the same computation served by the APIs.io cohort API. Briefs are published for rosters of 5 or more scored providers; below that a distribution is not meaningful.
Work with this as data
Every tag here is available over the APIs.io API and to AI agents over MCP.