Features
One write path for connected, searchable context.
RushDB turns structured data into connected graph context as it arrives. Choose the text fields you want indexed for semantic search, and give agents a live view of the labels, properties, and relationships they can query.
What's in the box.
Start with the capability your workflow needs. Each page explains the smallest useful path, the operational boundary, and the relevant documentation.
One feature set. Use the interface that fits.
RushDB database capabilities start with the REST API. Use the same product surface through the TypeScript or Python SDKs, or give MCP-compatible agents direct tool access to database operations.
REST API
Canonical surface
Use language-agnostic HTTP endpoints directly. OpenAPI documents records, relationships, transactions, AI search, and more.
Explore REST APITypeScript SDK
Browser + Node.js
Use a type-safe client for application code while keeping the same RushDB capabilities and query semantics.
Explore TypeScript SDKPython SDK
Sync + async
Use the Python client for backends, scripts, data workflows, and agent services without dropping down to raw HTTP.
Explore Python SDKMCP server
Agent-facing tools
Expose discovery, records, relationships, queries, bulk work, exports, and transactions to MCP-compatible clients.
Explore MCP serverAgents that know your data
before they query it.
RushDB builds a live ontology from every record you push. Agents read it once per session — and never construct a query blind again.
What the agent now knows
✓ Valid filter ranges
Agent knows price ranges from $9.99 to $2,499. It won't filter for price > $10,000 and return empty results.
✓ Real property names
Agent knows the field is "category", not "type" or "productType". No hallucinated field names. No silent query failures.
✓ Traversable relationships
Agent knows CUSTOMER → ORDER → PRODUCT is the real topology. Multi-hop queries built with confidence, not guesswork.
One call. One session. No hallucinated schema.
Fewer empty results. Fewer hallucinations. Agents that explain themselves.
The same SearchQuery that finds records also discovers what labels, properties, and relationships exist — making schema introspection a natural extension of the query you’re already writing. No separate schema API to learn.