Qdrant
Distribution-Based Score Fusion + RRF. Sparse vectors native; filtering via ANN graph modification.
At a glance
- Type
- Vector DB + DBSF + RRF
- Tier
- T1
- Section
- Vector-database infrastructure
- Created
- 2020-05
- Latest release
- v1.17.1 2026-03-27
- License
- Apache-2.0
- GitHub
- 31.1k★ +156/mo Rust
- Pricing
- Free + paid
- Funding
- $78M total Series B · 2026-03
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- overwrite
- unit
- chunk
- governance
- inspectable
- conflict
- overwrite
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
Rust-built — fastest of the OSS vector DBs in many benchmarks; strong filtering and hybrid search; clean API.
Cons
Smaller managed-cloud presence than Pinecone; ecosystem of integrations still maturing relative to Weaviate.
Claims & capabilities
GitHub repo surpassed 27,000★ in 2025 (~25k early 2025); maintains official benchmark suite (qdrant/benchmark + qdrant/vector-db-benchmark); added 35 new integrations in 2025 including official n8n node; uses ann-benchmarks dataset for cross-engine comparisons
Technical surface
- API surface
- REST, gRPC, SDK: Python, JS/TS, Rust, Go, Java, C#
- Backend storage
- custom (Rust-built HNSW + RocksDB metadata)
- Deployment
- Both
- Embedding model
- BYO
- Multi-tenancy
- Hardened unprivileged container per cluster with strict network policies; outbound restricted; paid plans on dedicated resources; Private Cloud option for air-gap
- MCP
- via official adapter — mcp-server-qdrant
- A2A
- no Google A2A (Agent2Agent) integration documented as of 2026-05.
- OpenTelemetry
- first-class — Prometheus + OTel
Compare Qdrant with…
Similar systems
Other vector-database infrastructure in the catalog, ranked by inbound references.
- 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.
- Pinecone T1
Managed vector DB. Cascading sparse + dense + rerank pipeline; pinecone-rerank-v0 .
- Chroma T1
Limited native hybrid (users build RRF custom). Fast Rust core (v2.5).
- LanceDB T1
Embedded vector DB (Arrow columnar). RRF reranker. Petabyte-scale on disk.
- 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).
- Milvus T1
Multi-vector columns (10 simultaneous). Native hybrid search (v2.5). CAGRA + Vamana GPU/CPU (v2.6).
Related systems
Referenced by (6)
- Agno (Phidata) Memory integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Mem0 depends on at runtime — adjacent-infrastructure cell: BYO LLM provider; bundles vector store (Qdrant default) and graph store (Neo4j optional)
- Mem0 Security / OpenMemory builds on — OpenMemory is the local self-hosted variant (Docker + FastAPI + Postgres + Qdrant)
- n8n AI Agent Memory integrates with — vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall
- OpenMemory depends on at runtime — adjacent-infrastructure cell: BYO LLM; self-hosted Postgres + Qdrant
- OpenMemory MCP builds on — Local Postgres + Qdrant cross-tool memory