- Home
- Vector Databases
- ManyVector
ManyVector
What it is
ManyVector is a vector database built on object storage, offering vector, full-text, and hybrid search for applications such as RAG pipelines, semantic search, recommendations, and AI agent memory. It uses HNSW approximate nearest-neighbour search and advertises sub-10ms p50 latency with 90%+ recall@10. BM25 supports full-text search, while hybrid search combines vector and text scores with RRF and metadata filters. Copy-on-write namespace branching enables snapshots, evaluation branches, and rollback without copying vector data. Supported object stores include AWS S3, Google Cloud Storage, Cloudflare R2, Azure Blob Storage, MinIO, Tigris, Wasabi, and S3-compatible services. ManyVector says it works with OpenAI, Cohere, and other embedding models or providers. Its Free Tier includes Python and TypeScript SDKs, 100M search queries per month, and requires customers to bring an object-store bucket. The maker says vectors and indexes remain in the customer's storage, not on ManyVector's disks. Managed SaaS data at rest uses AES-256 encryption, and client traffic uses TLS 1.2 or higher. ManyVector is a ManyLayers product.
For and against
For
- Supports vector, full-text, and hybrid search.
- Namespace branches support snapshots and rollback.
- Works with multiple object-store providers.
- Free Tier includes Python and TypeScript SDKs.
- Vectors and indexes stay in customer storage.
Against
- Free Tier requires a customer object-store bucket.
- Growth bills per query above the free allowance.
The verdict
ManyVector combines search modes with object-store storage and namespace branching. Its Free Tier includes 100M monthly queries, while enterprise deployment and support options are available for larger needs.
Who it suits
It suits teams building search, recommendation, RAG, or agent-memory systems that want object-store-backed vector data. Teams can use its managed service or, on Enterprise, deploy in a VPC or on-premises, including air-gapped operation after setup.
Plans and prices
Free Tier
100M search queries per month · no credit card · bring your own object store bucket · community support
Read 5 Oct 2026 · manyvector.com
Growth
100M free queries per month · unlimited vectors in your bucket · priority email support
Read 5 Oct 2026 · manyvector.com
Enterprise
volume discounts · self-hosted VPC or air-gapped deployment · SSO/SAML and SCIM · 99.9% uptime SLA
Read 5 Oct 2026 · manyvector.com
On the record
- Compliance
- The maker states that its managed SaaS platform is SOC 2 Type II certified and offers BAAs on Enterprise plans.manyvector.com · read 5 Oct 2026
- Data handling
- ManyVector says vectors and indexes are stored in the customer's object store and it does not store customer data on its disks.manyvector.com · read 5 Oct 2026
- Embedding compatibility
- ManyVector says it works with OpenAI, Cohere, and any embedding model or provider.manyvector.com · read 5 Oct 2026
- Full-text and hybrid search
- It offers BM25 full-text search and hybrid search combining vector and text scores with RRF and metadata filters.manyvector.com · read 5 Oct 2026
- Maker
- ManyVector is a product of ManyLayers.manyvector.com · read 5 Oct 2026
- Namespace branching
- Copy-on-write namespace branching supports snapshots, evaluation branches, and rollback without copying vector data.manyvector.com · read 5 Oct 2026
- Product
- ManyVector is a vector database on object storage with vector and full-text search.manyvector.com · read 5 Oct 2026
- SDKs
- The Free Tier includes Python and TypeScript SDKs.manyvector.com · read 5 Oct 2026
- Security
- The security page states managed SaaS data at rest is encrypted with AES-256 and client traffic uses TLS 1.2 or higher.manyvector.com · read 5 Oct 2026
- Self-hosting
- Enterprise customers can deploy in their own VPC or on-premises, including air-gapped operation after initial setup.manyvector.com · read 5 Oct 2026
- Storage integrations
- Supported object stores include AWS S3, Google Cloud Storage, Cloudflare R2, Azure Blob Storage, MinIO, Tigris, Wasabi, and S3-compatible stores.manyvector.com · read 5 Oct 2026
- Support
- Free Tier includes community support, Growth includes priority email support, and Enterprise includes dedicated support.manyvector.com · read 5 Oct 2026
- Use cases
- The maker lists RAG pipelines, semantic search, recommendations, and AI agent memory as use cases.manyvector.com · read 5 Oct 2026
- Vector search
- It uses HNSW approximate nearest-neighbour search and advertises sub-10ms p50 latency with 90%+ recall@10.manyvector.com · read 5 Oct 2026
