RAG
Variants seen in the corpus:
Retrieval Augmented GenerationRAG
Providers using this tag (90)
Ranked by API Evangelist rating — Exemplar and Strong are expanded by default.
Exemplar 2 Complete, well-documented, and agent-ready
Strong 8 Solid coverage with minor gaps
Developing 30 Usable, with meaningful gaps to close
Thin 29 Limited public surface area
Emerging 16 Early or largely undocumented
Minimal 5 Almost no public developer surface
APIs with this tag (46)
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 →
Exemplar 3 Complete, well-documented, and agent-ready
Cloudflare AI Search APIThe Cloudflare AI Search API provides fully managed retrieval-augmented generation (RAG) pipelines. Develop...Dify Chunks APIOperations for managing document chunks and child chunks. 9 operation(s) from the Dify Service API.Auth0 for AI AgentsIdentity and authorization product line for AI agents. Bundles Token Vault (delegated API credentials for G...
Strong 10 Solid coverage with minor gaps
Gravitee AI Agent ManagementGravitee AI Agent Management brings the API management discipline to agentic AI ecosystems. It is delivered...Fenergo Rag APIThe Rag API from Fenergo — 2 operation(s) for rag.NVIDIA NIM Embeddings APIOpenAI-compatible embeddings endpoint (/v1/embeddings) backed by NVIDIA NeMo Retriever text embedding model...NVIDIA NIM Reranking APINeMo Retriever cross-encoder reranking endpoint (/v1/ranking) for scoring candidate passages against a quer...Feedly Rag APIThe Rag API from Feedly — 1 operation(s) for rag.Vector Search Indexes APIManage vector search indexes for similarity search and retrieval-augmented generation workloads.Atomadic Tech Rag APIThe Rag API from Atomadic Tech — 1 operation(s) for rag.Blazing Bullet Private Limited Rag APIThe rag API from Blazing Bullet Private Limited — 4 operation(s) for rag.APIClaw Rag APIThe rag API from APIClaw — 4 operation(s) for rag.StepFun Vector Stores APIKnowledge-base (vector store) management — create/list/retrieve/delete stores and attach or remove files fo...
Developing 15 Usable, with meaningful gaps to close
Elium MCP ServerA remote Model Context Protocol server, announced 3 June 2026, served per tenant at https://{platform}.eliu...Factiva Retrieval APIProvides retrieval functionality that returns licensed news articles as part of trusted data sources in a r...LlamaCloud Index APIManaged vector index API for ingesting parsed documents into searchable LlamaCloud indexes. Supports standa...Amazon Bedrock Agent APIThe Amazon Bedrock Agent API provides operations for managing and configuring autonomous AI agents, knowled...Amazon Bedrock Agent Runtime APIThe Amazon Bedrock Agent Runtime API provides operations for invoking Bedrock agents and retrieving content...Vectara Chat APIMulti-turn conversational interface over a Vectara corpus that maintains chat history and produces grounded...RAGFlow HTTP APIThe RAGFlow RESTful HTTP API — 95 documented operations under /api/v1, authenticated with a tenant API key ...Arcee AI RAG APIThe RAG API from Arcee AI — 9 operation(s) for rag.Voyant.io Rag APIThe Rag API from Voyant.io — 7 operation(s) for rag.NationGraph RAG APIThe RAG API from NationGraph — 3 operation(s) for rag.TopK Dataset APIUnstructured document ingestion, semantic search, and grounded question answering. Upload document files (P...University of Amsterdam Rag APIThe rag API from University of Amsterdam — 4 operation(s) for rag.Trieve Message APIMessages are turns within a topic; the Message API drives RAG completions, streaming responses, and citatio...Trieve Topic APITopics persist conversational state for generative-AI chat sessions backed by a Trieve dataset.AI21 File Library APIManaged file storage for RAG workflows. Upload, list, retrieve, update, and delete documents that Maestro a...
Thin 9 Limited public surface area
Docling GraphTransform unstructured documents — once normalized to `DoclingDocument` — into validated, rich, queryable k...Docling LangChain IntegrationFirst-party LangChain document loader and chunker for Docling. Drops Docling output directly into LangChain...AI RAG Injector PluginAutomates retrieval-augmented generation by injecting retrieved context into prompts at the gateway, so app...LlamaIndex Python FrameworkLlamaIndex is an open-source Python framework for building LLM-powered applications including agents, RAG p...LlamaIndex TypeScript FrameworkLlamaIndex TypeScript is the JavaScript and TypeScript implementation of the LlamaIndex framework for build...LiteLLM Rag APIThe Rag API from LiteLLM — 2 operation(s) for rag.LiteLLM Vector Stores APIProvides /vector_stores endpoints for creating and managing vector stores, file operations within vector st...Tonic ValidateTonic Validate is an open-source RAG evaluation framework and metrics platform for measuring retrieval-augm...OpenLLMetry Vector Database InstrumentationsInstrumentations for vector databases used in retrieval-augmented generation pipelines — Chroma, Pinecone, ...
Emerging 9 Early or largely undocumented
Open WebUI APIREST API exposed by a self-hosted Open WebUI instance. Endpoints cover chat completions (proxying upstream ...Voyage AI Contextualized Embeddings APIEndpoint that embeds chunks while conditioning on surrounding document context, improving recall for long-d...Voyage AI Rerank APIReranking endpoint that scores a list of candidate documents against a query and returns relevance scores. ...Ragas Python LibraryThe Ragas Python library is the primary surface of the project, installed via `pip install ragas` and impor...Glean Chat APIMulti-turn generative chat over enterprise content with grounded answers, citations, and tool use.KAITO RAGEngine APIRAGEngine exposes endpoints for managing retrieval-augmented generation services with embedded vector datab...DeepEval (Confident AI)DeepEval is an open-source LLM evaluation package, paired with Confident AI as the hosted observability/eva...GalileoGalileo is an enterprise AI observability and evaluation engineering platform. The product line emphasizes ...RagasRagas is an open-source evaluation library focused on retrieval-augmented generation, described in its own ...
Companies reaching this through an API (19)
These companies publish an API, specification or operation carrying “RAG” 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.
APIClaw
Arcee AI
Atomadic Tech
Auth0
Azure Databricks
Blazing Bullet Private Limited
Cloudflare
Evals
Factiva
Feedly
Fenergo
Kong AI Gateway
LiteLLM
NationGraph
NVIDIA NIM
OpenLLMetry
StepFun
Tonic.ai
University of Amsterdam
Score breakdown
Frequency
59.0
log-scaled weighted occurrences
Breadth
2.0
spread across providers
Quality lift
39.3
mean composite of providers using it
Cohesion
11.5
strength of nearest seed neighbor
Where this tag sits
Related tags
Vector Search 29 co-occurrences
Retrieval 23 co-occurrences
Embeddings 22 co-occurrences
LLM 37 co-occurrences
Tools 15 co-occurrences
Enterprise Search 8 co-occurrences
Chat Completions 12 co-occurrences
Vectors 7 co-occurrences
Where this tag comes from
Provider tag97
Api tag46
Openapi tag10
Openapi op tag42
Cohort brief
Auto-generatedThe 89 providers in the APIs.io catalog tagged RAG, scored on the Kin Score. Every figure below is computed from the catalog — nothing here is written.
Providers
89
of 90 in the catalog
Mean Kin Score
37.7
+15.5 vs catalog 22.2
Mean Agent Readiness
24.7
+12.7 vs catalog 12
Spread
6.4–73.8
median 37.1 · σ 14.9
How the 89 split by band
Exemplar 2Strong 8Developing 30Thin 29Emerging 15Minimal 5
Facet averages, against the whole catalog
| Facet | This cohort | Catalog | Difference | Scored |
|---|---|---|---|---|
| Contract Quality | 38.8 | 17.2 | +21.6 | 89 |
| Developer Ergonomics | 41.4 | 23.2 | +18.2 | 89 |
| Operational Transparency | 25.4 | 13 | +12.4 | 89 |
| Access Clarity | 36.1 | 23.9 | +12.2 | 89 |
| Discoverability | 67.3 | 57.9 | +9.4 | 89 |
| Contract Governance | 9.6 | 6.5 | +3.1 | 89 |
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) | 33% | 13% | +20 |
| MCP server (first-party) | 34% | 12% | +22 |
| Agent Skills | 0% | 0% | 0 |
| OAuth scopes | 13% | 11% | +2 |
| Security | 98% | 98% | 0 |
| Arazzo workflows | 1% | 2% | -1 |
| Governance rules | 27% | 16% | +11 |
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 Dify 73.8
- 2 TranscriptFetch 67.7
- 3 WebCrawlerAPI 64.6
- 4 Nexla 64.3
- 5 Airia 64
- 6 Seekr 63.4
- 7 Space Frontiers 63.4
- 8 Pinecone 59.2
- 9 H2O.ai 56.5
- 10 Airweave 54.6
Top by Agent Readiness
- 1 Space Frontiers 68.9
- 2 Airweave 60.6
- 3 TranscriptFetch 56.9
- 4 LinqAlpha 55.5
- 5 Mixedbread 51.2
- 6 Airia 48.2
- 7 Seltz 46.9
- 8 WikiKV 46.9
- 9 OpenLaws 46.4
- 10 H2O.ai 44
All 90 members of this roster resolve to a provider in the
catalog; 89 carry a score (99%).
The figures above describe the scored members only.
Coverage caveat. 71 of 89 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. 71 of 89 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.