Skip to content

Latest commit

 

History

History
 
 

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

README.md

RushDB Logo

The memory layer for AI agents and apps.

Push any JSON. Get graph relationships and vector search — automatically. No schema. No pipeline. No glue code.

GitHub Stars Follow on X NPM PyPI

Website · Docs · Cloud · Examples


Your agent needs memory. The standard answer is three databases — Redis, a vector store, a graph DB — plus glue code to keep them in sync.

RushDB replaces all three. One API. Push JSON, query by meaning and by relationship, in a single call.

from rushdb import RushDB

db = RushDB('RUSHDB_API_KEY')

# One-time: tell RushDB to auto-embed 'output' on every write
db.ai.indexes.create(label='MEMORY', property_name='output')

# Store an agent action — no embedder, no vectors array
db.records.create(
    label='MEMORY',
    data={'agent_id': 'agent-42', 'topic': 'auth decision', 'output': summary_text},
)

# Recall semantically — just pass the query string
memories = db.ai.search({
    'labels': ['MEMORY'],
    'propertyName': 'output',
    'query': 'what did we decide about auth?',
    'where': {'agent_id': 'agent-42'},
    'limit': 10,
})

Repositories

Repo What it is
rushdb Platform — core API, dashboard, self-hosting
rushdb-python Python SDK
mcp-server MCP server for Claude, Cursor, Windsurf
examples Code samples across frameworks and use cases

MCP — connect to your AI client in 30 seconds

{
  "mcpServers": {
    "rushdb": {
      "command": "npx",
      "args": ["@rushdb/mcp-server"],
      "env": { "RUSHDB_API_KEY": "your-api-key-here" }
    }
  }
}

Get an API key at app.rushdb.com · hi@rushdb.com