{"family":"data","name":"Retrieval & Data Infrastructure","count":58,"license":"CC-BY-4.0","systems":[{"id":"activeloop-deep-lake--activeloop-ai","name":"Activeloop Deep Lake","url":"https://activeloop.ai","section":"Vector-database infrastructure","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Multimodal vector + serverless Postgres","license":"Apache-2.0","latest_release":"v4.7.4 (2026-08-25) — deeplake (PyPI)","deployment":"Both (self-hosted + managed cloud) — Apache-2.0 library and managed Deeplake cloud; Enterprise runs in your own VPC","pricing":"Hivemind Basic $0/month ($15 credits; 150k traces and 1.5M queries included, then $0.25 per 1k traces and 10k queries); Team $99/seat/month; Enterprise custom (own VPC)","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Deep Lake columnar format on object storage)","llm_lock":"","github":"activeloopai/deeplake — ~9.3k stars, last commit 2026-05","description":"Now positioned as Continual Learning Infrastructure, with three products: Deeplake Database, Hivemind Memory and Refinery Software Factory. Deep Memory feature optimises embedding space per use-case (+22% retrieval accuracy). Deep Lake PG unifies serverless Postgres (agent short-term state) + billion-scale vector search (long-term memory).","cited_cells":49,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/activeloop-deep-lake--activeloop-ai"},{"id":"algolia--algolia-com","name":"Algolia","url":"https://www.algolia.com/","section":"Search platforms (non-memory)","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Hosted search API","license":"proprietary (hosted SaaS); open-source API clients/codegen are MIT","latest_release":"not applicable — managed service (JS API client algoliasearch v5.60.0)","deployment":"Managed-only — hosted search-as-a-service API","pricing":"Free + paid","mcp_support":"via official adapter — Algolia MCP","a2a_support":"searched not found","backend_storage":"custom (proprietary sharded index)","llm_lock":"","github":"not applicable — no public engine repo (official API clients under github.com/algolia)","description":"Search-as-a-service API for instant search experiences — NeuralSearch (vector) + lexical. Adopted by 12000+ companies including LVMH, Stripe.","cited_cells":51,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/algolia--algolia-com"},{"id":"allegrograph-franz--allegrograph-com","name":"AllegroGraph (Franz)","url":"https://allegrograph.com/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"RDF triple/quad store + reasoning","license":"","latest_release":"","deployment":"Both (on-prem + cloud)","pricing":"Free tier + commercial licenses (quote-based)","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RDF triple store)","llm_lock":"","github":"","description":"RDF triple/quad store with RDFS++ / OWL reasoning. v8.4 (May 2025) added an NLQ interface.","cited_cells":44,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/allegrograph-franz--allegrograph-com"},{"id":"amazon-neptune-analytics--aws-amazon-com","name":"Amazon Neptune Analytics","url":"https://aws.amazon.com/neptune/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Vector + graph in one managed service","license":"","latest_release":"","deployment":"Managed-only","pricing":"Pay-per-use — billed per m-NCU-hour (1 m-NCU = 1 GB memory plus compute for 1 hour), $0.03 per m-NCU-hour in us-east-1 (16 m-NCU graph = $0.48/hour); paused graphs billed at 10% of compute","mcp_support":"yes — official AWS Labs Amazon Neptune MCP server (openCypher queries, schema and status for Neptune Analytics graphs)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (AWS Neptune managed)","llm_lock":"","github":"","description":"Vector index on graph nodes queryable via openCypher. Mem0 integration GA 2025; Cognee integration for agentic RAG. Combines semantic recall with multi-hop traversal in one managed service.","cited_cells":64,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/amazon-neptune-analytics--aws-amazon-com"},{"id":"apache-age--age-apache-org","name":"Apache AGE","url":"https://age.apache.org","section":"Knowledge-graph platforms","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"PostgreSQL graph extension","license":"Apache-2.0","latest_release":"v1.8.0 (release badge; date not captured)","deployment":"Self-hosted only — PostgreSQL extension (PG 11–18); some managed Postgres services (e.g. Azure) offer it","pricing":"Free (Apache License 2.0 open-source extension)","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"not supported","backend_storage":"Postgres","llm_lock":"","github":"apache/age — ~4.8k stars, active (commit date not captured)","description":"openCypher over Postgres. Pairs with pgvector for graph + vector hybrid retrieval. Azure Database for PostgreSQL ships AGE with ai_extension LLM functions for entity extraction directly in SQL.","cited_cells":50,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/apache-age--age-apache-org"},{"id":"arangodb--arangodb-com","name":"ArangoDB","url":"https://arango.ai/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Multi-model: graph + doc + KV + vector","license":"BSL-1.1 (source-available; each release converts to Apache-2.0 four years after release)","latest_release":"","deployment":"Both","pricing":"Pay-per-use","mcp_support":"yes — community ravenwits/mcp-server-arangodb","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RocksDB-backed multi-model)","llm_lock":"","github":"arangodb/arangodb — ~14.3k stars, active (commit date not captured)","description":"HybridGraphRAG combines vector search, graph traversal, full-text in one AQL query. ArangoGraphML for ML pipelines; LangChain integration. The company now brands itself Arango (Arango Contextual Data Platform unifying graph, vector, document and search), with ArangoDB as its database.","cited_cells":46,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/arangodb--arangodb-com"},{"id":"bge-baai--huggingface-co","name":"BGE (BAAI)","url":"https://huggingface.co/BAAI/bge-large-en-v1.5","section":"Embedding & reranker services","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"BAAI open embedding family","license":"MIT","latest_release":"FlagEmbedding v1.3.0 (pip; date not captured)","deployment":"Self-hosted only — open weights on Hugging Face (FlagEmbedding library); also served by third-party inference APIs","pricing":"free (open weights, MIT)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"FlagOpen/FlagEmbedding — ~12.2k stars, last README news 2025-03","description":"BAAI (Beijing Academy of AI) BGE family — bge-large/base/small + bge-m3 multilingual + bge-reranker. One of the most widely-used open embedding families.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/bge-baai--huggingface-co"},{"id":"chroma--trychroma-com","name":"Chroma","url":"https://www.trychroma.com/","section":"Vector-database infrastructure","tier":1,"status":"acquired","last_verified_at":"2026-10-29","type":"Embedded vector DB (Rust core)","license":"Apache-2.0","latest_release":"v1.6.0 (2026-10-13)","deployment":"Both (self-hosted + managed cloud) — OSS embedded/server; Chroma Cloud serverless; single-tenant/BYOC on Enterprise","pricing":"Chroma Cloud winding down: read-only from 2026-11-22, no reads after 2026-12-22, no new Cloud plans; open-source ChromaDB free (Apache-2.0)","mcp_support":"yes — official chroma-core/chroma-mcp (GitHub, Apache-2.0)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"SQLite (local) / custom cloud backend","llm_lock":"","github":"chroma-core/chroma — ~29.1k stars, last commit 2026-10","description":"Limited native hybrid (users build RRF custom). Fast Rust core (v2.5). Acquired by Replit (definitive agreement announced 2026-10-23); Chroma Cloud is winding down (writes disabled 2026-11-22, reads disabled 2026-12-22) while open-source ChromaDB continues under Apache-2.0.","cited_cells":61,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/chroma--trychroma-com"},{"id":"clarivate--clarivate-com","name":"Clarivate","url":"https://clarivate.com/","section":"Enterprise-search adjacencies","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Curated bibliographic metadata","license":"","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"yes — IPOne MCP servers: Derwent Patent MCP, CompuMark Trademark MCP, Darts-ip Litigation MCP","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"searched not found","llm_lock":"","github":"","description":"Bibliographic metadata curation (Web of Science, Derwent, Cortellis). Human editorial governance + journal-deindexing. Memory-adjacent — included as a curated-knowledge baseline.","cited_cells":35,"third_party_cells":9,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/clarivate--clarivate-com"},{"id":"cohere-embed--cohere-com","name":"Cohere Embed","url":"https://cohere.com/embed","section":"Embedding & reranker services","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Hosted embeddings API","license":"proprietary; Python SDK MIT","latest_release":"Embed 5 (2026-09-30)","deployment":"Both (self-hosted + managed cloud) — Cohere API and Model Vault; deployable in customer cloud via Amazon SageMaker, Azure AI Foundry and Oracle OCI","pricing":"Model Vault dedicated instances: Embed 5 Fast/Pro Small $3.00/hour ($2,000/month), Medium $5.00/hour ($3,250/month); Rerank 5 Fast Medium $4.00/hour ($2,500/month); embed models billed per token embedded, rerank per search on the API","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"cohere-ai/cohere-python — ~406 stars, last commit 2026-10 (official Python SDK)","description":"Cohere's hosted embedding models, now Embed 5 (2026-09-30; Pro and Fast tiers): text, image and fused text-plus-image inputs, 100+ languages, 128K-token context, Matryoshka output dimensions from 256 to 2048 with float, int8 and binary formats. Reranker API (Rerank 5).","cited_cells":22,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cohere-embed--cohere-com"},{"id":"coveo--coveo-com","name":"Coveo","url":"https://www.coveo.com","section":"Enterprise-search adjacencies","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"RAG-as-a-Service via hosted MCP","license":"","latest_release":"","deployment":"Managed-only","pricing":"Enterprise only","mcp_support":"yes — hosted Coveo MCP Server connecting AI agents (ChatGPT, Claude, Copilot) to Coveo retrieval","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom","llm_lock":"","github":"","description":"RAG-as-a-Service for AWS (Dec 2025) via hosted MCP server grounding Amazon Bedrock agents in enterprise knowledge. Passage retrieval + answer generation + ranked search + fetch in one API.","cited_cells":42,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/coveo--coveo-com"},{"id":"databricks-vector-search--databricks-com","name":"Databricks Vector Search (now Databricks AI Search)","url":"https://www.databricks.com/product/artificial-intelligence/ai-search","section":"Vector-database infrastructure","tier":1,"status":"renamed","last_verified_at":"2026-10-29","type":"Storage-optimised + Unity Catalog governance","license":"","latest_release":"","deployment":"Managed-only","pricing":"Pay-per-use DBUs — Standard $0.28/hour per unit (2M 768-dim vectors, 4 DBU/hour); Storage Optimized $1.28/hour per unit (64M vectors, 18.29 DBU/hour), effective US East prices","mcp_support":"yes — Databricks managed MCP server for AI Search indexes (/api/2.0/mcp/ai-search/{catalog}/{schema}/{index})","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"Delta Lake (columnar/lakehouse)","llm_lock":"","github":"","description":"Renamed Databricks AI Search: a fully managed search engine combining semantic vector, keyword (BM25) and hybrid search with reranking in one API. Storage-optimised index scaling to billions of vectors. Hosted MCP servers for UC functions, Genie, Vector Search. Agent framework integrates retrieval with Unity Catalog governance.","cited_cells":46,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/databricks-vector-search--databricks-com"},{"id":"dgraph--dgraph-io","name":"Dgraph","url":"https://docs.dgraph.io/","section":"Knowledge-graph platforms","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Graph + vector + Hypermode cloud","license":"Apache-2.0","latest_release":"v25.x (README: Dgraph is at version v25; exact patch and date not captured)","deployment":"Both (self-hosted OSS + Hypermode Cloud until Oct 2025 acquisition by Istari)","pricing":"searched not found","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Badger LSM-backed)","llm_lock":"","github":"dgraph-io/dgraph — ~21.8k stars, active (no archive notice; commit date not captured)","description":"Vector indexing on any node. Google Gen AI Toolbox integration; LangChain agent orchestration.","cited_cells":44,"third_party_cells":7,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dgraph--dgraph-io"},{"id":"diffbot--diffbot-com","name":"Diffbot","url":"https://www.diffbot.com/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Auto-extracted KG from web crawl","license":"","latest_release":"","deployment":"Managed-only","pricing":"Free $0/month (10,000 credits); Startup $299/month (250,000 credits, overage $0.001/credit); Startup Plus $899/month (1,000,000 credits, overage $0.0009/credit); Enterprise custom","mcp_support":"yes — official diffbot/diffbot-mcp server (extract, search_web, crawl, entity resolution tools)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom","llm_lock":"","github":"","description":"Auto-built knowledge graph from web crawl. 1T+ facts, 10B+ entities. GraphRAG-fine-tuned model based on open-source Llama 3.3.","cited_cells":40,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/diffbot--diffbot-com"},{"id":"elasticsearch-opensearch--elastic-co","name":"Elasticsearch","url":"https://www.elastic.co/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Mature hybrid search","license":"AGPL-3.0 / SSPL-1.0 / Elastic-2.0 (choice)","latest_release":"not applicable — managed service","deployment":"Both","pricing":"free (OSS) self-managed; Elastic Cloud paid (price pages not re-verified)","mcp_support":"yes — official Elastic Agent Builder MCP endpoint (Elastic 9.2+ / Serverless); older elastic/mcp-server-elasticsearch deprecated","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Lucene-backed)","llm_lock":"","github":"elastic/elasticsearch — ~78k stars, active (commit date not captured)","description":"Mature hybrid (BM25 + vector) implementations. RRF + weighted combination. Elastic ELSER sparse model.","cited_cells":54,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/elasticsearch-opensearch--elastic-co"},{"id":"falkordb--falkordb-com","name":"FalkorDB","url":"https://www.falkordb.com/","section":"Knowledge-graph platforms","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"GraphRAG-native, sub-140ms multi-hop","license":"SSPL-1.0 (source-available)","latest_release":"","deployment":"Both (self-hosted + managed cloud) — OSS server/Docker; FalkorDB Cloud (free trial)","pricing":"Free + paid","mcp_support":"yes — official FalkorDB/FalkorDB-MCPServer (MIT)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"Redis","llm_lock":"","github":"FalkorDB/FalkorDB — ~10.5k stars, active (commit date not captured)","description":"Native GraphRAG SDK. Graph-memory backend for Mem0; MCP server via Graphiti integration; context graphs for long-term agent memory.","cited_cells":50,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/falkordb--falkordb-com"},{"id":"glean--glean-com","name":"Glean","url":"https://www.glean.com/","section":"Enterprise-search adjacencies","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Enterprise search + per-user KG","license":"","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"native (first-party) — Glean MCP server","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom","llm_lock":"","github":"","description":"Enterprise search with 100+ connectors. Personalised per-user knowledge graph. No governance layer.","cited_cells":43,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/glean--glean-com"},{"id":"gte-alibaba-nlp--huggingface-co","name":"GTE (Alibaba-NLP)","url":"https://huggingface.co/thenlper/gte-large","section":"Embedding & reranker services","tier":3,"status":"active","last_verified_at":"2026-10-27","type":"Alibaba general text embeddings","license":"Apache-2.0 (Alibaba-NLP gte-multilingual, gte-modernbert, gte-Qwen2); MIT (original thenlper/gte-large/base/small)","latest_release":"gte-modernbert-base / gte-reranker-modernbert-base (2025-01-20) — Hugging Face","deployment":"Self-hosted only — open weights on Hugging Face","pricing":"Free — open weights","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"searched not found","description":"Alibaba DAMO Academy's GTE family — open-weight multilingual embedding models; gte-large/base/small + Qwen-based gte-Qwen2.","cited_cells":12,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/gte-alibaba-nlp--huggingface-co"},{"id":"hugging-face-inference-api-embeddings--huggingface-co","name":"Hugging Face Inference API (Embeddings)","url":"https://huggingface.co/docs/api-inference","section":"Embedding & reranker services","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"HF hosted embeddings","license":"proprietary service; huggingface_hub SDK Apache-2.0; Text Embeddings Inference Apache-2.0","latest_release":"v2.3.0 (2026-10-23) — huggingface_hub","deployment":"Both (self-hosted + managed cloud) — managed Inference Providers and Inference Endpoints; self-hosted Text Embeddings Inference (TEI)","pricing":"Inference Providers pay-as-you-go at provider rates with no Hugging Face markup; PRO users get $2.00/month credits, Team/Enterprise $2.00 per seat; Inference Endpoints billed hourly per instance","mcp_support":"yes — official Hugging Face MCP Server (huggingface/hf-mcp-server)","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"huggingface/text-embeddings-inference — ~5.1k stars, last commit 2026-10","description":"HF's hosted Inference API and Inference Endpoints — serve any model from the Hub including the BGE/GTE/E5 embedding families.","cited_cells":21,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hugging-face-inference-api-embeddings--huggingface-co"},{"id":"jina-ai-embeddings--jina-ai","name":"Jina AI Embeddings","url":"https://jina.ai/embeddings/","section":"Embedding & reranker services","tier":1,"status":"acquired","last_verified_at":"2026-10-29","type":"Open embedding models + API","license":"mixed — most recent open-weight models CC-BY-NC-4.0 (v3, v5-omni, v5-text, clip-v2, colbert-v2, reranker-v3; commercial licence via Elastic); jina-embeddings-v4 under the Qwen Research License (its model card says the initial CC-BY-NC-4.0 label was an error); some older models Apache-2.0","latest_release":"jina-embeddings-v5-omni (nano and small; 2026-05-07); reranker jina-reranker-v3.5 (2026-07-27)","deployment":"Both (self-hosted + managed cloud) — hosted Jina API; open weights and jina-on-prem air-gapped Docker/K8s; SageMaker","pricing":"Hosted API: prepaid token packages with a free trial key and optional auto-recharge (pricing model since 2025-05-06); also on AWS SageMaker and Microsoft Azure; Jina On-Prem containers sold through Elastic Sales","mcp_support":"yes — official jina-ai/MCP remote server (mcp.jina.ai/v1; embeddings, rerank, reader, search tools)","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"no dedicated embeddings repo (weights on Hugging Face); jina-ai/MCP ~841 stars, jina-ai/reader ~11.9k","description":"Jina AI's embedding family — jina-embeddings-v3 (multilingual), jina-clip-v2 (text+image), jina-colbert-v2. Open-weights + hosted API + ColBERT-style.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/jina-ai-embeddings--jina-ai"},{"id":"kuzu--kuzudb-github-io","name":"Kuzu","url":"https://kuzudb.github.io","section":"Knowledge-graph platforms","tier":2,"status":"archived","last_verified_at":"2026-10-29","type":"Embedded graph DB + sub-3ms recall","license":"MIT","latest_release":"0.11.3 (final release; repository archived 2025-10-10)","deployment":"Self-hosted only (embedded library; no managed cloud at time of acquisition)","pricing":"Free (MIT-licensed open source); acquired by Apple so no commercial cloud","mcp_support":"via community port","a2a_support":"not supported","backend_storage":"custom (embedded native graph)","llm_lock":"","github":"kuzudb/kuzu — ~4.0k stars, archived 2025-10-10 (read-only)","description":"Embedded property-graph database (Cypher) with a built-in vector index and full-text search, widely used as an embedded store for agent memory and GraphRAG. The kuzudb/kuzu repository was archived on 2025-10-10 after Apple acquired the company; 0.11.3 is the final release and earlier releases remain usable.","cited_cells":48,"third_party_cells":26,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/kuzu--kuzudb-github-io"},{"id":"lancedb--lancedb-com","name":"LanceDB","url":"https://lancedb.com/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Embedded Arrow-columnar vector DB","license":"Apache-2.0","latest_release":"v0.40.0 (2026-10-07)","deployment":"Both (self-hosted + managed cloud) — embedded OSS library; LanceDB Enterprise as Managed or BYOC","pricing":"free (OSS); LanceDB Enterprise/Cloud pricing via sales (no public price list)","mcp_support":"yes — official reference server lancedb/lancedb-mcp-server (basic, 3 tools)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Lance columnar format on object storage)","llm_lock":"","github":"lancedb/lancedb — ~11.3k stars, last commit 2026-10","description":"Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.","cited_cells":80,"third_party_cells":8,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lancedb--lancedb-com"},{"id":"lucidworks-conversational-q-a-ai-agent--lucidworks-com","name":"Lucidworks Conversational Q&A AI Agent","url":"https://lucidworks.com/platform/ai-agents/ai-powered-conversational-qa-agent-built-for-enterprises","section":"Enterprise-search adjacencies","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Session-history conversational memory atop RAG","license":"","latest_release":"","deployment":"Both (self-hosted + managed cloud) — Lucidworks Platform SaaS; self-hosted Fusion","pricing":"searched not found","mcp_support":"yes — Lucidworks MCP server exposes Fusion query pipelines to Claude and other MCP clients","a2a_support":"","backend_storage":"custom (Lucidworks Fusion / Solr-backed)","llm_lock":"Grounded-only answer style avoids hallucination on technical specs; PDP-embedded keeps shoppers on page; multimodal PDF/table/chart understanding handles real product manuals.","github":"","description":"Enterprise Q&A agent powered by Luci patent-pending ultra-precise RAG. Embeds on product detail pages; consumes technical PDFs, spec sheets, images, tables, charts, graphs and product manuals. Maintains session history for multi-turn follow-ups; refuses out-of-scope queries via prompt-injection guard.","cited_cells":49,"third_party_cells":11,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lucidworks-conversational-q-a-ai-agent--lucidworks-com"},{"id":"marqo--marqo-ai","name":"Marqo","url":"https://www.marqo.ai","section":"Vector-database infrastructure","tier":2,"status":"deprecated","last_verified_at":"2026-10-29","type":"Multimodal vector via single API","license":"Apache-2.0","latest_release":"","deployment":"Managed-only — commercial Marqo platform; the self-hosted OSS engine is deprecated","pricing":"Pay-per-use","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Vespa-backed)","llm_lock":"","github":"marqo-ai/marqo — ~5.0k stars, OSS deprecated (no further updates)","description":"Marqo's open-source multimodal (text + image) vector search engine is deprecated and gets no further updates; the company now sells an AI-native ecommerce search and product discovery platform with personalization from clickstream and purchase data. The engine handled embedding generation internally behind a single API.","cited_cells":44,"third_party_cells":8,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/marqo--marqo-ai"},{"id":"meilisearch--meilisearch-com","name":"Meilisearch","url":"https://www.meilisearch.com","section":"Enterprise-search adjacencies","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Open-source semantic + hybrid search","license":"MIT (Community Edition) / BSL-1.1 (source-available, Enterprise Edition parts)","latest_release":"v1.53.1 (2026-08-13)","deployment":"Both (self-hosted + managed cloud) — OSS binary/Docker; Meilisearch Cloud","pricing":"Free + paid","mcp_support":"yes — official meilisearch/meilisearch-mcp (MIT)","a2a_support":"not supported","backend_storage":"custom (LMDB-backed engine, Rust)","llm_lock":"","github":"meilisearch/meilisearch — ~59.6k stars, active (31 commits to main after v1.53.1)","description":"Semantic + hybrid search GA (2025). Automatic embedding generation + caching via OpenAI / HuggingFace / Ollama. Multi-modal (text + images); hybrid rank fusion; conversational RAG built in.","cited_cells":53,"third_party_cells":7,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/meilisearch--meilisearch-com"},{"id":"memgraph--memgraph-com","name":"Memgraph","url":"https://memgraph.com/","section":"Knowledge-graph platforms","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"In-memory GraphRAG + native vector search","license":"BSL-1.1 (source-available, Community); Enterprise under proprietary MEL","latest_release":"","deployment":"Both","pricing":"Free + paid","mcp_support":"yes — official MCP server in memgraph/ai-toolkit","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (in-memory native graph)","llm_lock":"","github":"memgraph/memgraph — ~4.4k stars, active (commit date not captured)","description":"In-memory GraphRAG engine. Memgraph 3.0 adds native vector search alongside graph traversal. LangChain toolkit.","cited_cells":52,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/memgraph--memgraph-com"},{"id":"milvus--milvus-io","name":"Milvus","url":"https://milvus.io/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Multi-vector + hybrid + GPU","license":"Apache-2.0","latest_release":"v3.0.3 (2026-10-14)","deployment":"Both (self-hosted OSS + Zilliz Cloud managed)","pricing":"free (OSS); managed via Zilliz Cloud (free tier, then usage-based)","mcp_support":"yes — official zilliztech/mcp-server-milvus (GitHub)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (object-storage backed; etcd metadata; Pulsar/Kafka log)","llm_lock":"","github":"milvus-io/milvus — ~46k stars, last commit 2026-10","description":"Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).","cited_cells":59,"third_party_cells":10,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/milvus--milvus-io"},{"id":"mindbreeze-inspire--mindbreeze-com","name":"Mindbreeze InSpire","url":"https://www.mindbreeze.com","section":"Enterprise-search adjacencies","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Hybrid + entitlement-aware + KG","license":"","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"yes — Mindbreeze Model Context Protocol Server (permission-aware enterprise context for AI assistants and agents)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom","llm_lock":"","github":"","description":"Hybrid keyword + vector retrieval with entitlement-aware filtering. Unified enterprise knowledge graph linking documents, tickets, records. RAG prompt orchestration built in.","cited_cells":39,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mindbreeze-inspire--mindbreeze-com"},{"id":"mistral-embed--mistral-ai","name":"Mistral Embed","url":"https://mistral.ai/news/mistral-embed","section":"Embedding & reranker services","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Mistral embedding API","license":"proprietary; SDK Apache-2.0","latest_release":"v3.5.0 (2026-10-25) — mistralai (PyPI)","deployment":"searched not found","pricing":"mistral-embed $0.10 per 1M tokens; Codestral Embed $0.15 per 1M tokens; batch API 50% cheaper","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"mistralai/client-python — ~775 stars, last commit 2026-10 (official Python SDK)","description":"Mistral AI's hosted embedding API — mistral-embed; available via Mistral La Plateforme and Azure AI.","cited_cells":19,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mistral-embed--mistral-ai"},{"id":"mixedbread-ai--mixedbread-com","name":"Mixedbread AI","url":"https://www.mixedbread.com/","section":"Embedding & reranker services","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Embedding + reranker API","license":"proprietary API; open-weight models Apache-2.0 (mxbai-embed-large-v1, mxbai-rerank-v2); SDKs Apache-2.0","latest_release":"v0.78.0 (2026-09-14) — @mixedbread/sdk","deployment":"Both (self-hosted + managed cloud) — managed Mixedbread API (BYOC/BYOB on Enterprise); Apache-2.0 open-weight models self-hostable","pricing":"Starter free ($5 one-time credits); Scale $20/month (includes $20 credits, then pay-as-you-go); Enterprise custom. Indexing $1.50/1M tokens (Fast) or $3 (High Quality); semantic search $4 per 1K queries (+$3.50 with rerank); grep search $0.10 per 1K queries","mcp_support":"yes — official Mixedbread MCP Server connecting AI assistants to Mixedbread Stores/Search","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"searched not found","description":"Agentic search platform that ingests PDFs, decks, video, code, Slack and Drive and returns evidence to agents. Built on its own models and database: Wholembed V3 (late-interaction, omnimodal) embeddings, mxbai-rerank listwise reranker, a trained search agent and Silo, an S3-native multi-vector engine. Earlier open-weight models (mxbai-embed-large, mxbai-rerank) and a paid API.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mixedbread-ai--mixedbread-com"},{"id":"mongodb-atlas-vector-search--mongodb-com","name":"MongoDB Atlas Vector Search","url":"https://www.mongodb.com/products/platform/atlas-vector-search","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Vector embedded in document DB","license":"","latest_release":"","deployment":"Both (self-hosted + managed cloud) — Atlas managed; Atlas Local deployments with vector search (auto-embedding via Voyage AI)","pricing":"Pay-per-use","mcp_support":"yes — official mongodb-js/mongodb-mcp-server (Apache-2.0)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"MongoDB (with Lucene-based vector index)","llm_lock":"","github":"","description":"Agent memory store for both short-term (document) and long-term (vector). LangGraph checkpointer for stateful agents. Vector search extended to Community Edition (Sept 2025).","cited_cells":48,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mongodb-atlas-vector-search--mongodb-com"},{"id":"nebulagraph--nebula-graph-io","name":"NebulaGraph","url":"https://nebula-graph.io","section":"Knowledge-graph platforms","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Graph + vector + text hybrid retrieval","license":"Apache-2.0","latest_release":"v3.8.0 OSS line (version referenced by repo docs; release date not captured)","deployment":"Both (self-hosted + NebulaGraph Cloud)","pricing":"OSS (Apache-2.0) + NebulaGraph Enterprise (commercial)","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RocksDB-backed distributed graph)","llm_lock":"","github":"vesoft-inc/nebula — ~12.4k stars, active (commit date not captured)","description":"v5.2 adds graph-vector-text hybrid retrieval natively. MCP server for Claude/GPT agents. GraphRAG in three lines of code.","cited_cells":44,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/nebulagraph--nebula-graph-io"},{"id":"neo4j--neo4j-com","name":"Neo4j","url":"https://neo4j.com/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Property graph + vectors + Aura Agent","license":"GPL-3.0 (Community Edition); Enterprise Edition proprietary","latest_release":"2026.07 CalVer series (current default branch; exact patch and date not captured)","deployment":"Both (self-hosted + managed cloud) — Community/Enterprise self-managed; Neo4j Aura cloud","pricing":"Free + paid","mcp_support":"yes — official neo4j/mcp (product team); Neo4j Labs also ships neo4j-contrib/mcp-neo4j","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (native graph store)","llm_lock":"","github":"neo4j/neo4j — ~17.2k stars, active (default branch 2026.07)","description":"Property graph DB with Cypher; native vector search; Aura Agent + MCP server for graph-as-memory. $100M GenAI investment in 2025.","cited_cells":82,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/neo4j--neo4j-com"},{"id":"nomic-embed--nomic-ai","name":"Nomic Embed","url":"https://huggingface.co/nomic-ai/nomic-embed-text-v1.5","section":"Embedding & reranker services","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Open embedding + atlas","license":"Apache-2.0","latest_release":"v3.9.0 (2025-11-11) — nomic (PyPI)","deployment":"Both (self-hosted + managed cloud) — Apache-2.0 open weights on Hugging Face; hosted models via Nomic Agent API (Business/Enterprise)","pricing":"Open weights free; Nomic platform Free, Individual $20/month, Business $40/user/month (25-seat minimum, includes Agent API), Enterprise custom","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"nomic-ai/nomic — ~1.9k stars, last commit 2025-11","description":"Nomic's open-weight embedding models (nomic-embed-text-v1.5, nomic-embed-vision), distributed on Hugging Face. Nomic itself has pivoted to domain-specific agents for architecture, engineering and construction firms (Nomic Platform, Agent API); the nomic.ai/embed page is gone.","cited_cells":19,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/nomic-embed--nomic-ai"},{"id":"ontotext-graphdb-graphwise--graphwise-ai","name":"Ontotext GraphDB / Graphwise","url":"https://graphwise.ai/","section":"Knowledge-graph platforms","tier":1,"status":"acquired","last_verified_at":"2026-10-29","type":"RDF store + real-time inference","license":"proprietary; GraphDB Free (free-to-use non-commercial option) and Enterprise Edition; every edition needs a licence file (Free licence emailed on request)","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"yes — GraphDB 11.4 supports custom MCP prompt templates (defined via REST) for AI agents","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RDF triple store)","llm_lock":"","github":"","description":"RDF graph database with real-time inference, now a component of the Graphwise Platform. Ontotext and Semantic Web Company (PoolParty) joined forces as Graphwise in 2024; Oakley Capital took a majority stake in 2026.","cited_cells":43,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/ontotext-graphdb-graphwise--graphwise-ai"},{"id":"openai-embeddings--platform-openai-com","name":"OpenAI Embeddings","url":"https://platform.openai.com/docs/guides/embeddings","section":"Embedding & reranker services","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"OpenAI embedding API","license":"proprietary; SDKs Apache-2.0","latest_release":"v3.39.0 (2026-10-26) — openai (PyPI)","deployment":"Managed-only — OpenAI API","pricing":"text-embedding-3-small $0.02 per 1M tokens; text-embedding-3-large $0.13 per 1M tokens","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"openai/openai-python — ~32k stars, last commit 2026-10 (official Python SDK)","description":"OpenAI's hosted embedding API — text-embedding-3-small, text-embedding-3-large. Most widely used commercial embedding API in OSS RAG/memory stacks.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-embeddings--platform-openai-com"},{"id":"opensearch-aws--opensearch-org","name":"OpenSearch","url":"https://opensearch.org/","section":"Search platforms (non-memory)","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Open Elasticsearch fork","license":"Apache-2.0","latest_release":"searched not found","deployment":"searched not found","pricing":"free (OSS); Amazon OpenSearch Service billed separately by AWS","mcp_support":"yes — official opensearch-project/opensearch-mcp-server-py (Apache-2.0)","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"opensearch-project/OpenSearch — ~13.7k stars, active (commit date not captured)","description":"AWS-led fork of Elasticsearch 7 — Apache-licensed; k-NN plugin, OpenSearch ML, neural-search. Substrate beneath AWS OpenSearch Service.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/opensearch-aws--opensearch-org"},{"id":"palantir-ontology--palantir-com","name":"Palantir Ontology","url":"https://www.palantir.com/docs/foundry/ontology/overview","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Operational digital twin","license":"","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"yes — Ontology MCP (exposes Ontology to external agents) and Palantir MCP (palantir/palantir-mcp)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"searched not found","llm_lock":"","github":"","description":"Proprietary operational ontology — semantic objects + kinetic actions wired to microservices. Not open-standards KG; closed platform.","cited_cells":43,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/palantir-ontology--palantir-com"},{"id":"pgvector--gh-pgvector-pgvector","name":"pgvector","url":"https://github.com/pgvector/pgvector","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"PostgreSQL vector extension","license":"PostgreSQL","latest_release":"v0.8.6 (2026-07-29)","deployment":"Self-hosted only — PostgreSQL extension; also offered inside managed Postgres (Supabase, AWS RDS, Azure, Neon, etc.)","pricing":"free (OSS)","mcp_support":"yes — community Postgres MCP servers with pgvector tools (e.g. MOmayr/mcp-postgres-pgvector)","a2a_support":"not supported","backend_storage":"Postgres","llm_lock":"","github":"pgvector/pgvector — ~23.5k stars, last commit 2026-07 or later (0.8.7 unreleased)","description":"Stores embeddings alongside relational + full-text data. HNSW + IVFFlat ANN indexes. Used as agent conversation memory via LangChain + MCP. Foundation of Supabase AI and many self-hosted RAG stacks.","cited_cells":55,"third_party_cells":10,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pgvector--gh-pgvector-pgvector"},{"id":"pinecone--pinecone-io","name":"Pinecone","url":"https://www.pinecone.io/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Managed vector DB + cascading retrieval","license":"","latest_release":"","deployment":"Managed-only — serverless SaaS on AWS/GCP/Azure; BYOC (GA 2026-09) runs in the customer's cloud account","pricing":"Starter free (2 GB, 2M WU/1M RU per mo); Builder $20/mo; Standard $50/mo minimum; Enterprise $500/mo minimum","mcp_support":"yes — official @pinecone-database/mcp (npm) plus per-Assistant remote MCP servers","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (proprietary serverless vector index, S3-backed)","llm_lock":"","github":"","description":"Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .","cited_cells":55,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pinecone--pinecone-io"},{"id":"qdrant--qdrant-tech","name":"Qdrant","url":"https://qdrant.tech/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Vector DB + DBSF + RRF","license":"Apache-2.0","latest_release":"v1.19.2 (2026-10-05)","deployment":"Both (self-hosted + managed cloud) — OSS engine; Qdrant Managed Cloud, Hybrid Cloud and Private Cloud","pricing":"Free tier forever (single node, 1 GB RAM / 4 GB disk); Standard usage-based hourly billing; Premium has minimum spend; Hybrid/Private Cloud via sales","mcp_support":"yes — official qdrant/mcp-server-qdrant (GitHub, Apache-2.0)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Rust-built HNSW + RocksDB metadata)","llm_lock":"","github":"qdrant/qdrant — ~34.9k stars, last commit 2026-10","description":"Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.","cited_cells":59,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/qdrant--qdrant-tech"},{"id":"quickwit--quickwit-io","name":"Quickwit","url":"https://quickwit.io/","section":"Search platforms (non-memory)","tier":2,"status":"acquired","last_verified_at":"2026-10-29","type":"Log + event search engine","license":"Apache-2.0","latest_release":"searched not found","deployment":"Self-hosted only — OSS distributed search engine on object storage","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"quickwit-oss/quickwit — ~11.6k stars, active (commit date not captured)","description":"Open-source distributed search engine for logs/traces — cloud-native (object storage as primary tier). Acquired by Datadog 2024.","cited_cells":19,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/quickwit--quickwit-io"},{"id":"sajari-now-search-io--search-io","name":"Sajari (now Search.io)","url":"https://www.search.io/","section":"Search platforms (non-memory)","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"Site search platform","license":"searched not found","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"sajari/sajari-sdk-go — ~4 stars, last commit 2019-05","description":"Site-search platform (formerly Sajari) with the Neuralsearch vector engine. Acquired by Algolia in September 2022 and folded into Algolia's hybrid search; search.io now redirects to algolia.com.","cited_cells":7,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sajari-now-search-io--search-io"},{"id":"searchunify--searchunify-com","name":"SearchUnify","url":"https://www.searchunify.com/","section":"Enterprise-search adjacencies","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Agentic enterprise search + KCS","license":"","latest_release":"","deployment":"Managed-only","pricing":"Enterprise only","mcp_support":"yes — official SearchUnify MCP server (su-mcp) exposing search and analytics tools","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"searched not found","llm_lock":"","github":"","description":"Agentic enterprise search with Knowbler — quality checks via the KCS (Knowledge-Centered Service) standard. Most explicit governance features in the segment.","cited_cells":40,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/searchunify--searchunify-com"},{"id":"sentence-transformers--sbert-net","name":"Sentence Transformers","url":"https://www.sbert.net/","section":"Embedding & reranker services","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Open embedding training framework","license":"Apache-2.0","latest_release":"searched not found","deployment":"Self-hosted only — Python library (pip)","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"huggingface/sentence-transformers — ~19.2k stars, active (commit date not captured)","description":"Reimers & Gurevych's library for training sentence embeddings — substrate under most open-weight embedding models. Now under Hugging Face.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sentence-transformers--sbert-net"},{"id":"sinequa--sinequa-com","name":"Sinequa","url":"https://www.sinequa.com","section":"Enterprise-search adjacencies","tier":1,"status":"acquired","last_verified_at":"2026-10-28","type":"Hybrid retrieval + agentic RAG","license":"","latest_release":"","deployment":"Both","pricing":"Enterprise only","mcp_support":"yes — Sinequa MCP Server exposing 200+ connectors and search to MCP clients","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom","llm_lock":"","github":"","description":"Hybrid retrieval combining dense vector + keyword + graph traversal + multimodal. Agentic RAG grounding AI agents in internal knowledge. SOC 2 / ISO 27001 compliant.","cited_cells":53,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sinequa--sinequa-com"},{"id":"snowflake-cortex-search--docs-snowflake-com","name":"Snowflake Cortex Search","url":"https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Hybrid vector + keyword + semantic rerank","license":"","latest_release":"","deployment":"Managed-only","pricing":"Pay-per-use","mcp_support":"yes — official Snowflake-managed MCP server (Cortex Agents MCP); Snowflake-Labs/mcp community server deprecated","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"Snowflake (columnar)","llm_lock":"","github":"","description":"Hybrid vector + keyword + semantic reranking. Cortex Agents (GA Nov 2025) orchestrate over Cortex Search for unstructured data. No separate vector infra needed inside Snowflake.","cited_cells":45,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/snowflake-cortex-search--docs-snowflake-com"},{"id":"stardog--stardog-com","name":"Stardog","url":"https://www.stardog.com/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"RDF semantic platform + Voicebox AI","license":"","latest_release":"","deployment":"Both","pricing":"Stardog Free (renewable 1-year license, commercial use allowed, no HA/caching/backups); Enterprise on-prem and cloud quote-based","mcp_support":"yes — official Stardog Cloud MCP server (stardog-union/stardog-cloud-mcp; remote setup in beta)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RDF triple store)","llm_lock":"","github":"","description":"RDF-native semantic platform with SHACL validation, virtual graphs, and the Voicebox AI assistant. $32.5M funding. Pitches itself as a governed-knowledge layer.","cited_cells":47,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/stardog--stardog-com"},{"id":"supabase-vector--supabase-com","name":"Supabase Vector","url":"https://supabase.com/modules/vector","section":"Search platforms (non-memory)","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Postgres + pgvector cloud","license":"Apache-2.0 (Supabase stack); vectors via pgvector (PostgreSQL licence)","latest_release":"searched not found","deployment":"Both (self-hosted + managed cloud) — Supabase Cloud or self-hosted Supabase stack","pricing":"searched not found","mcp_support":"yes — official supabase/mcp (Apache-2.0)","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"supabase/supabase — ~108k stars, active (commit date not captured)","description":"Supabase's managed pgvector — combined Postgres + vector store; popular default for OSS LLM apps. Supabase $80M Series C 2024.","cited_cells":22,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/supabase-vector--supabase-com"},{"id":"tantivy--gh-quickwit-oss-tantivy","name":"Tantivy","url":"https://github.com/quickwit-oss/tantivy","section":"Search platforms (non-memory)","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Rust full-text search library","license":"MIT","latest_release":"searched not found","deployment":"Self-hosted only — embedded Rust full-text search library","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"quickwit-oss/tantivy — ~16.2k stars, active (commit date not captured)","description":"Rust port of Lucene — embedded full-text search engine. Underlies Quickwit, Lnx, Bayard. Used in Meilisearch and many in-process search engines.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/tantivy--gh-quickwit-oss-tantivy"},{"id":"tigergraph--tigergraph-com","name":"TigerGraph","url":"https://www.tigergraph.com/","section":"Knowledge-graph platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Massively parallel graph + GSQL","license":"","latest_release":"","deployment":"Both","pricing":"Community Edition free; Savanna free trial; Savanna $45 per GB/month and Savanna Business Critical $126 per GB/month (24x7, US/Tier 1); Enterprise via sales","mcp_support":"yes — official tigergraph/tigergraph-mcp server (stdio and Streamable HTTP, built on pyTigerGraph)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (native parallel graph)","llm_lock":"","github":"","description":"Parallel graph DB with GSQL/GQL. CoPilot for entity extraction. Free community edition.","cited_cells":46,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/tigergraph--tigergraph-com"},{"id":"topquadrant-topbraid-edg--topquadrant-com","name":"TopQuadrant TopBraid EDG (now TQ Data Foundation)","url":"https://www.topquadrant.com/","section":"Knowledge-graph platforms","tier":1,"status":"renamed","last_verified_at":"2026-10-29","type":"Ontology-native governance","license":"","latest_release":"","deployment":"Both (on-prem + Azure Marketplace SaaS)","pricing":"Enterprise only — modular packages (Metadata Mgmt, Reference Data Mgmt, Vocabulary Mgmt, Business Glossaries)","mcp_support":"yes — TQ Data Foundation MCP connector serves governed context to agents","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (RDF)","llm_lock":"","github":"","description":"Ontology-native semantic governance suite (formerly TopBraid EDG, now TQ Data Foundation) built on RDF, OWL and SHACL; serves governed context to agents via MCP, a Python SDK and REST.","cited_cells":39,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/topquadrant-topbraid-edg--topquadrant-com"},{"id":"turbopuffer--turbopuffer-com","name":"Turbopuffer","url":"https://turbopuffer.com/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Object-storage-first vector DB","license":"","latest_release":"","deployment":"Managed-only — multi-tenant cloud; single-tenant and BYOC (in customer cloud) on Enterprise","pricing":"Usage-based with monthly minimums: Launch $16/month, Scale $256/month, Enterprise from $4,096/month (35% usage premium); calculator rates storage up to $0.33/GB, writes up to $2.00/GB, queries up to $1.00/PB","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (object-storage native vector engine)","llm_lock":"","github":"","description":"Object-storage-first vector DB. Powers Notion and Cursor. SPFresh indexing; ~10× cost reduction vs. memory-resident peers.","cited_cells":42,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/turbopuffer--turbopuffer-com"},{"id":"typesense--typesense-org","name":"Typesense","url":"https://typesense.org/","section":"Search platforms (non-memory)","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Open-source typo-tolerant search","license":"GPL-3.0","latest_release":"searched not found","deployment":"Both (self-hosted + managed cloud) — OSS server; Typesense Cloud","pricing":"searched not found","mcp_support":"yes — community suhail-ak-2/mcp-typesense-server","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"typesense/typesense — ~27k stars, active (commit date not captured)","description":"Open-source search engine focused on typo-tolerance and ease of use — Typesense Cloud commercial; rising Algolia alternative.","cited_cells":19,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/typesense--typesense-org"},{"id":"vald--vald-vdaas-org","name":"Vald","url":"https://vald.vdaas.org/","section":"Search platforms (non-memory)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Cloud-native distributed vector search","license":"Apache-2.0","latest_release":"searched not found","deployment":"Self-hosted only — Kubernetes-native distributed vector search engine","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"vdaas/vald — ~1.7k stars, active (commit date not captured)","description":"Yahoo Japan's open-source distributed vector search engine — built on NGT; Kubernetes-native; horizontal scaling.","cited_cells":14,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vald--vald-vdaas-org"},{"id":"vespa--vespa-ai","name":"Vespa","url":"https://vespa.ai","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Unified vector + lexical + structured + ranking","license":"Apache-2.0","latest_release":"not applicable — managed service","deployment":"Both (self-hosted + managed cloud) — OSS self-hosted; Vespa Cloud (free trial)","pricing":"Pay-per-use","mcp_support":"no first-party MCP adapter published as of 2026-05; community connectors may exist.","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (Vespa proton engine)","llm_lock":"","github":"vespa-engine/vespa — ~7.1k stars, active (releases from master Mon–Thu)","description":"Combines vector ANN, lexical, structured filtering, and ML-learned ranking in one distributed system. Integrated chunking + layered ranking for RAG. No separate embedding infra needed.","cited_cells":46,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vespa--vespa-ai"},{"id":"voyage-ai-mongodb--voyageai-com","name":"Voyage AI (MongoDB)","url":"https://www.voyageai.com/","section":"Embedding & reranker services","tier":1,"status":"acquired","last_verified_at":"2026-10-27","type":"Premium embedding + reranker API","license":"proprietary; SDKs MIT (Python, TypeScript)","latest_release":"v0.5.0 (2026-07-10) — voyageai (PyPI)","deployment":"Both (self-hosted + managed cloud) — Voyage API; AWS and Azure Marketplace model packages in customer VPC; on-prem and model licensing by request","pricing":"Per-token with free allowance: voyage-4-large $0.12/1M tokens, voyage-4 $0.06, voyage-4-lite $0.02 (first 200M tokens free); rerank-3 $0.05/1M, rerank-3-lite $0.02/1M; multimodal $0.12/1M tokens + $0.60/1B pixels","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"voyage-ai/voyageai-python — ~114 stars, last commit 2026-10 (official Python SDK)","description":"Specialised embedding and reranker provider — voyage-3, voyage-multilingual, voyage-finance, voyage-law, voyage-code. Acquired by MongoDB Feb 2025 for $220M.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/voyage-ai-mongodb--voyageai-com"},{"id":"weaviate--weaviate-io","name":"Weaviate","url":"https://weaviate.io/","section":"Vector-database infrastructure","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Hybrid vector DB + learned ranking","license":"BSD-3-Clause","latest_release":"v1.40.2 (2026-10-21)","deployment":"Both (self-hosted + managed cloud) — OSS (Docker/K8s); Weaviate Cloud shared (Free/Flex) and dedicated (Premium)","pricing":"Free cluster $0 (100k objects, 1 GB RAM, 10 GB disk); Flex pay-as-you-go from $45/mo; Premium prepaid via sales; OSS free","mcp_support":"yes — official MCP server built into Weaviate since v1.38 (Streamable HTTP at /v1/mcp)","a2a_support":"no Google A2A (Agent2Agent) integration documented as of 2026-05.","backend_storage":"custom (LSM-backed vector + inverted index)","llm_lock":"","github":"weaviate/weaviate — ~16.8k stars, last commit 2026-10","description":"Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.","cited_cells":58,"third_party_cells":6,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/weaviate--weaviate-io"}]}