Weaviate

https://weaviate.io/

Hybrid Search 2.0 with learned ranking. BM25 + vector in unified index.

Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 59 cited facts, 6 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2016-03 repo fix
Latest release
v1.40.2 (2026-10-21) repo fix
License
BSD-3-Clause repo fix
Freshness
2026-10-26 fix
Layer
model-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
Protocols
mcp-server vendor fix
Compliance
hipaa vendor fix

When to use

Optimised for: low-latency similarity search + scale

Anti-fit: not for relational / graph-heavy queries (vector-first by design)

Pros & cons

Pros

OSS-first managed and self-hosted vector DB with native hybrid (vector + keyword) and module ecosystem (Q&A, summarization, classification).

Cons

Module surface area can lead to feature drift; smaller enterprise sales presence than Pinecone.

Claims & capabilities

Made 2024 Forbes AI 50 List alongside OpenAI/Cohere/HuggingFace/Mistral/LangChain; combines vector search with knowledge-graph-style schema for contextual enrichment; not consistently top in pure-vector benchmarks but strong on hybrid use cases; emerged 2019

Technical surface

API surface
REST, GraphQL, gRPC, SDK: Python, JS/TS, Go, Java
Backend storage
custom (LSM-backed vector + inverted index)
Deployment
Both (self-hosted + managed cloud) — OSS (Docker/K8s); Weaviate Cloud shared (Free/Flex) and dedicated (Premium)
Embedding model
multiple supported
Multi-tenancy
Tenant-per-collection (multi-tenancy feature) gives logical isolation without separate clusters; Dedicated Cloud option for hard isolation
MCP
yes — official MCP server built into Weaviate since v1.38 (Streamable HTTP at /v1/mcp)
A2A
no Google A2A (Agent2Agent) integration documented as of 2026-05.
OpenTelemetry
first-class — Prometheus + OTel

Compare Weaviate with…

Similar systems

Other vector-database infrastructure in the catalog, ranked by inbound references.

  • Qdrant T1

    Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.

  • Chroma T1

    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.

  • pgvector T1

    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.

  • Milvus T1

    Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).

  • Pinecone T1

    Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .

  • MongoDB Atlas Vector Search T1

    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).

Sources (58 cited facts, 6 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-26
    • Latest release “v1.37.2 2026-04-23” → “v1.40.2 (2026-10-21)” source
    • Pricing “Free + paid” → “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” source
    • Deployment “Both” → “Both (self-hosted + managed cloud) — OSS (Docker/K8s); Weaviate Cloud shared (Free/Flex) and dedicated (Premium)” source
    • MCP support “via official adapter — weaviate-mcp” → “yes — official MCP server built into Weaviate since v1.38 (Streamable HTTP at /v1/mcp)” source
    #258

Related systems

References (28)

  • Anthropic Claude (foundation models) integrates with — Weaviate's integrations / model-provider docs list Anthropic Claude (foundation models) as an integration. (verified 2026-10-29)
  • Anyscale integrates with — Weaviate's integrations / model-provider docs list Anyscale as an integration. (verified 2026-10-29)
  • Arize Phoenix integrates with — Weaviate's integrations / model-provider docs list Arize Phoenix as an integration. (verified 2026-10-29)
  • Cohere Command R+ / Command A integrates with — Weaviate's integrations / model-provider docs list Cohere Command R+ / Command A as an integration. (verified 2026-10-29)
  • Comet ML integrates with — Weaviate's integrations / model-provider docs list Comet ML as an integration. (verified 2026-10-29)
  • Composio integrates with — Weaviate's integrations / model-provider docs list Composio as an integration. (verified 2026-10-29)
  • Confident AI / DeepEval integrates with — Weaviate's integrations / model-provider docs list Confident AI / DeepEval as an integration. (verified 2026-10-29)
  • CrewAI integrates with — Weaviate's integrations / model-provider docs list CrewAI as an integration. (verified 2026-10-29)
  • DeepSeek R1 / V3 family integrates with — Weaviate's integrations / model-provider docs list DeepSeek R1 / V3 family as an integration. (verified 2026-10-29)
  • DSPy integrates with — Weaviate's integrations / model-provider docs list DSPy as an integration. (verified 2026-10-29)
  • Haystack (framework) integrates with — Weaviate's integrations / model-provider docs list Haystack (framework) as an integration. (verified 2026-10-29)
  • Hugging Face Inference API (Embeddings) integrates with — Weaviate has a Hugging Face model-provider integration that calls the Hugging Face Inference API for embeddings. (verified 2026-10-29)
  • Jina AI Embeddings integrates with — Weaviate's integrations / model-provider docs list Jina AI Embeddings as an integration. (verified 2026-10-29)
  • LangChain (framework) integrates with — Weaviate's integrations / model-provider docs list LangChain (framework) as an integration. (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — Weaviate's integrations / model-provider docs list LlamaIndex (framework) as an integration. (verified 2026-10-29)
  • Mem0 integrates with — Weaviate's integrations / model-provider docs list Mem0 as an integration. (verified 2026-10-29)
  • Microsoft Semantic Kernel integrates with — Weaviate's integrations / model-provider docs list Microsoft Semantic Kernel as an integration. (verified 2026-10-29)
  • Mistral Large 2 / Mixtral family integrates with — Weaviate's integrations / model-provider docs list Mistral Large 2 / Mixtral family as an integration. (verified 2026-10-29)
  • n8n (AI agent flows) integrates with — Weaviate's integrations / model-provider docs list n8n (AI agent flows) as an integration. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Weaviate's integrations / model-provider docs list OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) as an integration. (verified 2026-10-29)
  • Patronus AI integrates with — Weaviate's integrations / model-provider docs list Patronus AI as an integration. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Weaviate's integrations / model-provider docs list Phidata as an integration. (verified 2026-10-29)
  • Ragas integrates with — Weaviate's integrations / model-provider docs list Ragas as an integration. (verified 2026-10-29)
  • Replicate integrates with — Weaviate's integrations / model-provider docs list Replicate as an integration. (verified 2026-10-29)
  • TruLens integrates with — Weaviate's integrations / model-provider docs list TruLens as an integration. (verified 2026-10-29)
  • Voyage AI (MongoDB) integrates with — Weaviate's integrations / model-provider docs list Voyage AI (MongoDB) as an integration. (verified 2026-10-29)
  • Weights & Biases integrates with — Weaviate's integrations / model-provider docs list Weights & Biases as an integration. (verified 2026-10-29)
  • xAI Grok 4 integrates with — Weaviate's integrations / model-provider docs list xAI Grok 4 as an integration. (verified 2026-10-29)

Referenced by (17)

  • Agno (Phidata) Memory integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
  • Arcade.dev integrates with — Arcade docs have a Weaviate integration page. (verified 2026-10-29)
  • Bifrost (Maxim AI) integrates with — Bifrost docs have a Weaviate vector-database integration page for semantic caching. (verified 2026-10-29)
  • Cohere Embed integrates with — Cohere docs "Integrating Embedding Models with Other Tools": Weaviate and Cohere guide. (verified 2026-10-29)
  • CrewAI integrates with — CrewAI docs have a Weaviate vector search tool page. (verified 2026-10-29)
  • Dify integrates with — Dify self-host VECTOR_STORE supports `weaviate` as the knowledge-base vector store. (verified 2026-10-29)
  • DSPy integrates with — DSPy ships a Weaviate retriever module (dspy/retrievers/weaviate_rm.py). (verified 2026-10-29)
  • Haystack (framework) integrates with — Haystack integrations directory has a Weaviate integration page ("Use a Weaviate database with Haystack"). (verified 2026-10-29)
  • LangChain (framework) integrates with — LangChain docs have a Weaviate integration provider page (Open-source vector database with GraphQL). (verified 2026-10-29)
  • Langflow integrates with — Langflow components bundle: Weaviate vector store component. (verified 2026-10-29)
  • LlamaIndex (framework) integrates with — LlamaIndex has an official vector store integration package llama-index-vector-stores-weaviate in its repo. (verified 2026-10-29)
  • Mastra integrates with — Mastra repo ships the @mastra/weaviate vector store package. (verified 2026-10-29)
  • Mem0 integrates with — Mem0 docs have a Weaviate vector store page for Mem0 open source. (verified 2026-10-29)
  • Microsoft Semantic Kernel integrates with — Semantic Kernel docs list an out-of-the-box Weaviate vector store connector. (verified 2026-10-29)
  • n8n (AI agent flows) integrates with — n8n built-in AI cluster node: Weaviate Vector Store node. (verified 2026-10-29)
  • OpenLLMetry (Traceloop) integrates with — OpenLLMetry's What's Supported page lists Weaviate as instrumented out of the box. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Agno ships a weaviate vector DB integration module (agno.vectordb.weaviate). (verified 2026-10-29)