Skip to main content
LambdaDB is the vector lake for AI memory. Store, search, and version AI knowledge and memory, from small experiments to production, without managing always-on servers. Documents, vectors, and indexes live in durable object storage, while on-demand compute handles indexing and retrieval.

​
🗃️ Store and search AI knowledge and memory

Object storage

Store text, embeddings, and their metadata with flexible schema support across 9 different index types.

Vector search

k-NN search with cosine, euclidean, dot product, max inner product metrics.

Full-text search

Multi-language analysis (English, Korean, Japanese, standard).

Hybrid search

Combines vector + lexical with score normalization (RRF, Min-Max, L2).

Multi-field vector search

Search across multiple vector fields simultaneously.

Sparse vector search

Efficient high-dimensional sparse vector storage and search.

​
🏢 Enterprise features

​
Backup & recovery

  • Continuous backups: Automatic collection-level backups with 30-day retention by default.
  • Point-in-time branches: Create a branch from a committed snapshot at or before a chosen time within the retention period.
  • Data versioning: Use branches for isolated writes, immutable tags for pinned snapshots, and mutable aliases for stable read names.

​
Operation & management

  • Serverless-native architecture: Zero infrastructure management required without paying for idle resources.
  • Configurable rate limiting: Project-level usage controls managed in LambdaDB Cloud.
  • RESTful API: Simple HTTP-based interface with comprehensive SDKs.