OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Rushdb

RushDB is a graph-and-vector database built on Neo4j that stores JSON as typed, queryable records with inferred relationships and semantic search. It provides a memory layer for AI agents and applications.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rushdb — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use RushDB when an agent or application needs JSON-backed records that can be searched semantically and traversed through inferred relationships, or when a single data layer is preferable to maintaining separate stores for those query patterns.

Who it is for

  • AI-agent developers who need to store and retrieve persistent context.
  • Application developers who want to query JSON records through graph relationships or semantic search.
  • Teams importing nested JSON or CSV data for connected-record queries.

Documented uses

  • Store agent actions and context as records that can be retrieved by meaning.
  • Import nested JSON and represent nested objects as linked records.
  • Search data using relationship filters, semantic search or a combination of both.
  • Run aggregations and group records for analytical queries.
Before you choose

Requirements & limits

The README describes a managed cloud option and a self-hosting path using Docker with a Neo4j instance. JavaScript and Python SDK installation examples are provided.

  • The documented data model combines graph relationships and vector search around records stored from JSON.
  • The README presents schema inference for nested JSON, rather than requiring a schema and migration step for that import workflow.
  • Cloud and self-hosted paths are described; self-hosting calls for Docker and Neo4j.
  • The repository is public, while the README's Apache 2.0 license badge specifically identifies the JavaScript SDK.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a cloud SDK connection for agent memory

Prepare a JavaScript or Python client to connect to RushDB Cloud.

Before you start

  • A RushDB Cloud API key.
  • Node.js with npm for the JavaScript SDK, or Python with pip for the Python package.

Steps

  1. Install the JavaScript package with npm install @rushdb/javascript-sdk, or install the Python package with pip install rushdb.

  2. Create the RushDB client using the API key.

Expected outcome

A client instance is configured for use with the documented records operations.

Guide limitations

  • These steps cover installation and client initialization only; they do not verify a successful connection or perform a write or search.
  • The documented self-hosting path instead requires Docker and a Neo4j instance.
Documentation 1 ↗
Source-based practical guide

Store and semantically retrieve an agent memory

Use the documented JavaScript flow to index a text field, store a memory record and search it by meaning.

Before you start

  • The JavaScript SDK installed and a RushDB client initialized with an API key.
  • A text value to store as the memory output.

Steps

  1. Create an AI index for the MEMORY label and output property.

  2. Create a MEMORY record containing the agent identifier, session or topic context, action and output text.

  3. Call vectorSearch on the output property with a natural-language query and an agent identifier filter.

Expected outcome

The documented flow requests semantically relevant memory records while filtering by agent identifier.

Guide limitations

  • The guide reflects the README example and is not a compatibility or execution test.
  • The example uses the RushDB API key and does not document self-hosted configuration.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
RushdbStore agent actions and context as records that can be retrieved by meaning.Cloud, Docker, Self-hosted, ServerThe README describes a managed cloud option and a self-hosting path using Docker with a Neo4j instance. JavaScript and Python SDK installation examples are provided.
KektordbSave and retrieve semantic memories across agent sessions.Self-hosted, ServerThe README describes self-hosted use and displays an Apache 2.0 license badge.
LongbowStore and retrieve dense or sparse vectors with HNSW search.Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
rush-db/rushdb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction