Agent Memory
Knowledge graph memory for AI agents. Create entities, observations, and relations to build persistent understanding across executions.
Actions
| Name | Description |
|---|---|
create_entitiesCreate one or more entities in the knowledge graph. | Create one or more entities in the knowledge graph. |
add_observationsAdd observations to existing entities in the knowledge graph. | Add observations to existing entities in the knowledge graph. |
create_relationsCreate relations between entities in the knowledge graph. | Create relations between entities in the knowledge graph. |
searchSearch entities by query string across names, types, and observations. | Search entities by query string across names, types, and observations. |
read_graphRead the entire knowledge graph including all entities and relations. | Read the entire knowledge graph including all entities and relations. |
get_entityGet a specific entity by name from the knowledge graph. | Get a specific entity by name from the knowledge graph. |
delete_entitiesDelete entities by name from the knowledge graph. Also removes related relations. | Delete entities by name from the knowledge graph. Also removes related relations. |
delete_observationsRemove specific observations from an entity. | Remove specific observations from an entity. |
delete_relationsDelete specific relations from the knowledge graph. | Delete specific relations from the knowledge graph. |
Quick Start
import { WeavzClient } from '@weavz/sdk'
const weavz = new WeavzClient({ apiKey: 'wvz_...' })
const result = await weavz.actions.execute({
integrationName: 'agent-memory',
actionName: 'create_entities',
input: { /* ... */ },
connectionId: 'conn_id',
workspaceId: 'ws_id',
})Related Integrations
Works well with
Frequently Asked Questions
How do I connect Agent Memory to my app?
Use Weavz Hosted Connect for No Auth authentication. Install the SDK, create a connection through the connect portal or API, then execute actions programmatically.
What actions does Agent Memory support?
Agent Memory supports 9 actions including Create Entities, Add Observations, Create Relations, Search, Read Graph, and more.
Can I use Agent Memory with AI agents?
Yes. Add Agent Memory to an MCP server in TOOLS mode or CODE mode. CODE mode provides 80-98% context reduction with 3 meta-tools for efficient agent access.
What authentication does Agent Memory use?
Agent Memory uses No Auth. Weavz handles token management, refresh, and secure credential storage automatically.
How much does the Agent Memory integration cost?
The Agent Memory integration is included on all Weavz plans including the free tier with 1,000 actions per month. No credit card required.
Connect Agent Memory in 2 minutes
Get 1,000 free actions every month. No credit card required.