[ DURABLE AGENT MEMORY · GRAPH + VECTOR SEARCH · LIVE SCHEMA]

Memory for agents.Instant.

Write JSON. Get a graph, semantic search, and queryable schema — automatically.
No pipeline. No separate stores. No glue code.

json input
 
push
graph — auto-linked nodes
MEMORYAGENTACTIONSESSIONSTEPTOPICTAGSSCOREINDEX
vector embeddings
The memory problem

Agent tooling changes.
Memory should not.

RushDB is a durable memory layer for AI agents: structured records, relationships, semantic search, and schema discovery from the JSON your application already produces.

Typical agent stack

Memory split across systems.

App records, session state, embeddings, metadata, tool output, and relationships drift across separate stores.

Application memory layer

Store context

Application DB

facts, history, metadata

Redis

session state, cache

Vector DB

embeddings, similarity search

Your code owns:

sync · embed · index · join · retry

With RushDB

Write JSON or CSV. Get Records.

Store messages, tool results, documents, entities, and events as Records with the structure your workflow needs.

Any JSON
Records
Typed fields
Searchable text
Graph links
Schema discovered on write

No forced memory schema. Send nested JSON as often as your workflow produces it. RushDB keeps structure, typed fields, searchable text, and relationships together.

Change the stack without rebuilding memory.

Memory lives outside any one model, framework, MCP client, or provider session, so the next agent can continue from the same durable context.

Durable memory layer

Model changes

Every provider reads the same records, relationships, and searchable context.

Framework changes

SDK, MCP, and application workflows share one durable memory layer.

Workflow changes

Keep context available without replaying transcripts or migrating session state.

See how RushDB connects your data
Quickstart

Running in minutes.

Install

Add the SDK for TypeScript, Python, or use the REST API directly — no extra dependencies.

Push

Write any JSON object. RushDB parses field types, builds the graph structure, and indexes vectors server-side on the same write.

Recall

Query by meaning, by graph relationship, or both in a single call using the same SearchQuery shape every time.

install
push · recall
Use cases

Start with the problem you have.

Persistent memory, graph-aware retrieval, and AI app data without stitching together a database, cache, vector store, and sync jobs.

Agents forget between runs

Persist decisions, tool outputs, entities, and state as records your next workflow can reuse.

Explore agent memory

RAG misses connected context

Retrieve related records and entities, not only the nearest similar chunks.

Explore graph-aware RAG

AI apps create sync debt

Add search, relationships, and structured context without maintaining another pipeline.

Explore AI-powered apps
Explore all use cases

Give your agent memory.