Vald
Yahoo Japan's open-source distributed vector search engine — built on NGT; Kubernetes-native; horizontal scaling.
At a glance
- Type
- Cloud-native distributed vector search
- Tier
- T3
- Section
- Search platforms (non-memory)
- Created
- 2019
- Latest release
- searched not found
- License
- Apache-2.0
- GitHub
- searched not found
- Pricing
- searched not found
- Funding
- searched not found
Taxonomy
- storage
- n/a
- retrieval
- n/a
- persistence
- n/a
- update
- n/a
- unit
- n/a
- governance
- n/a
- conflict
- n/a
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
searched not found
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- searched not found
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other search platforms (non-memory) in the catalog, ranked by inbound references.
- PostgreSQL pgvector T1
Open-source Postgres extension for vector similarity — HNSW and IVFFlat indexes; widely deployed (Supabase, Neon, AWS RDS, Crunchy, Azure).
- Algolia T1
Search-as-a-service API for instant search experiences — NeuralSearch (vector) + lexical. Adopted by 12000+ companies including LVMH, Stripe.
- Elastic Cloud T1
Elastic's managed Elasticsearch cloud — vector search (ELSER reranker, dense vectors), full-text, observability, security. Public (NYSE: ESTC).
- Meilisearch (Cloud) T2
French open-source search engine — fast, typo-tolerant, vector search beta. Meilisearch Cloud commercial.
- OpenSearch (AWS) T1
AWS-led fork of Elasticsearch 7 — Apache-licensed; k-NN plugin, OpenSearch ML, neural-search. Substrate beneath AWS OpenSearch Service.
- Qdrant Cloud T1
Hosted managed Qdrant cloud — multi-cloud single-tenant clusters; hybrid cloud private deployment; widely used as a memory backend (Mem0 default).