RushDB Agent Setup

Give any AI agent persistent, graph-structured memory — sessions, decisions, tasks, entities, and preferences — stored in RushDB and queryable by meaning.

Unlike flat key-value stores, RushDB memory auto-links nested JSON into a relationship graph, survives across conversations, and lets agents recall context by traversal or semantic similarity: "What did we decide about auth? What's related to that service?"


Step 1 — Connect the MCP Server

Web clients (ChatGPT, Claude.ai) — no install required

Use the hosted OAuth endpoint. No API key in config — you authenticate with your RushDB account.

ChatGPT: Settings → Connectors → Add connector → https://mcp.rushdb.com/mcp

Claude.ai: Settings → Integrations → Add integration → https://mcp.rushdb.com/mcp

Local clients (Claude Desktop, Cursor, VS Code)

Requires a RushDB API key → app.rushdb.com

Claude Desktop — edit ~/Library/Application Support/Claude/claude_desktop_config.json:

Cursor — add to .cursor/mcp.json:

VS Code — add to .vscode/mcp.json:


Step 2 — Install Skills (recommended)

Skills give your agent built-in knowledge of RushDB's query syntax, memory patterns, and data modeling conventions — so you don't have to explain them in every session. They work best alongside the MCP server: skills tell the agent how; the MCP server gives it the tools.

Or via npm:

Start a new agent session after installation so the skills are discovered.

SkillWhat it enables
rushdb-agent-memorySession patterns, memory model, recall strategies
rushdb-query-builderBuild findRecords filters, aggregations, and semantic searches
rushdb-data-modelingDesign labels, properties, relationships, and nested schemas
rushdb-faceted-searchBuild faceted filter UIs from live property metadata
rushdb-domain-templateDesign a schema for any domain through guided conversation

Bootstrap Prompt

After the MCP server is connected, paste this prompt to your agent to initialize memory.


Memory Model

RushDB memory is a property graph. Each memory is a Record with a Label (type) and flat JSON properties (primitives and lists of primitives). Nested JSON is automatically normalized: each nested object becomes its own record, and parent → child relationships are created for you.

Recommended Labels

LabelWhat it stores
SESSIONA conversation or work session
DECISIONA decision made, with rationale and timestamp
ENTITYA named thing — person, service, project, concept
TASKA work item with status and assignee
PREFERENCEA persistent user preference or constraint
OBSERVATIONA raw note or finding
PLANA proposed sequence of steps
ARTIFACTA produced output — code, doc, design

Auto-linking Example

A single importJson call with nested labels creates a full linked subgraph:

RushDB creates 1 SESSION, 1 DECISION, 2 ENTITY, and 1 TASK record — all linked automatically.


Recall Patterns

"What did we decide about X?"

"What sessions have we had?"

"What do I prefer?"

"What happened in the last 7 days?"


Semantic Search (Memory by Meaning)

$contains is exact substring match — fast, no setup. Use it for IDs, slugs, and known keywords.

Semantic search finds memories by meaning even when exact words differ — "auth system" matches a record that says "we chose Clerk for login". It requires a one-time index setup per label + property.

Create an index (one-time, per project)

The agent calls createEmbeddingIndex, polls getEmbeddingIndexStats until indexedRecords === totalRecords, then runs a test semanticSearch.

Query by meaning

Combine with metadata filters

Candidates are narrowed by metadata first, then ranked by similarity.


End-of-Session Pattern

Ask your agent to save the session before closing:


Resources