[ instant graph + vector storage ]

Memory for agentsand apps. Instant.

Push any JSON or CSV. Get graph relationships and vector search automatically.
No schema. No pipeline. No glue code.

Quick Tutorial Try RushDB Cloud →

Ingest anything

Push flat objects, nested trees, or batches. Types inferred, graph built — no schema needed.

Auto-linked graph

Nested objects become linked records automatically. Traverse relationships in queries.

Semantic search

Index any text property and query by meaning. Combine with field filters.

ACID transactions

Wrap any combination of writes and reads. Nothing persists if any step fails.

Choose your interface

Every interface gives you the same capabilities — pick the one that fits your stack.

npm

TypeScript SDK

Full type safety for Node.js and browsers. Async/await API with zero config.

Type-safe query builder
Browser + Node.js
ESM & CommonJS

Get started

pip

Python SDK

Ergonomic client for backend scripts and data workflows. Sync and async.

Sync & async client
Pandas-friendly output
Pipeline-ready

Get started

HTTP

REST API

Language-agnostic HTTP access. Works from any stack with curl or fetch.

OpenAPI spec
Full CRUD + search
Transaction support

Get started

MCP

MCP Server

Model Context Protocol server. Give any LLM agent direct database access.

Claude, GPT & Cursor
Schema auto-exposed
One-command deploy

Get started

Start learning

Guides, tutorials, and concept explanations to get you productive fast.

Quick Tutorial

First write → graph → semantic search in under 10 minutes.

Start here

Tutorials

Hands-on guides: RAG pipelines, deployment, vector search, agent memory.

Browse tutorials

Concepts

How RushDB stores, links, and queries data — records, properties, graphs.

Learn concepts

Cloud

RushDB Cloud

Free tier — 100,000 KU/month and 2 projects. No credit card required.

Self-Hosted

Run on your infrastructure

No KU limits, no billing. Deploy with Docker in minutes on your own stack.

Deployment guide