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.

Ontology API

Agents 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.

POST/api/v1/ai/ontology/md

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.

✕ Before
✓ After
Agent filters price > 50,000 — 0 results, no explanation
Agent knows max price is $2,499 — constructs meaningful range query
Agent queries productType field — doesn't exist, silent fail
Agent queries category — real field, real values
Agent traverses USER → ITEM — relationship doesn't exist
Agent traverses CUSTOMER → ORDER → PRODUCT — exact topology

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.

Give your agent memory.