Storage
Auto chunking and embeddings
Send raw text. We split on sentence boundaries, embed with production models, and store vectors in pgvector. You never touch chunk size or embedding config.
< 30msmedian store latency
AI memory infrastructure
Databaset remembers what your users say, finds it by meaning when it matters, and hands your model ready-to-use context. No vector DB sprint. No chunking scripts. No rebuilding the same pipeline on every project.
Free tier includes 10,000 memories/month. No credit card required.
Recall query
"tech stack"
Waiting for recall…
3
Lines to integrate
One npm install, one API key
< 50ms
Recall latency
p95 across all regions
99.9%
Uptime SLA
On Growth and Enterprise plans
∞
Users per API key
Isolated memory per userId
Works with every AI model and framework
Live demo
Store a few facts, ask a question, and watch Databaset recall relevant context before answering. No signup required.
Stored
Stop stitching Pinecone, chunking scripts, and retrieval glue. Ship memory like you ship auth.
Storage
Send raw text. We split on sentence boundaries, embed with production models, and store vectors in pgvector. You never touch chunk size or embedding config.
< 30msmedian store latency
Retrieval
Queries match by meaning, not keywords. Recency, memory type, and contradiction handling are built in. No extra config required.
Dashboard
Search, filter, inspect similarity scores, and delete. Debug what your model actually knows about each user.
100%of memories visible in UI
Security
Per-user isolation, hashed API keys, TLS 1.3, AES-256 at rest. SOC2 path on Enterprise.
Scale
Multi-tenant by design. Separate prod and staging with appId namespaces.
Install, store, recall, ship. No vector DB project required.
One package. No other dependencies.
npm install @databaset/sdkSend any text. We handle chunking, embedding, and storage automatically.
await memory.store(userId, "User prefers dark mode")Semantic search returns the most relevant memories.
const context = await memory.recall(userId, userMessage)Inject context into Claude, GPT-4, Gemini, or any model.
const reply = await anthropic.messages.create({ system: `You know this about the user: ${context}`, messages: [{ role: 'user', content: userMessage }]})Pricing
Start free, grow when you're ready. No surprise bills.
Perfect for side projects and prototypes
For production apps with real users
For teams scaling AI products
Custom limits and dedicated support
Get started free
10,000 memories free every month. SDK, dashboard, and docs included. No credit card.