Agent Memory
Knowledge graph memory for AI agents. Create entities, observations, and relations to build persistent understanding across executions. Persistence scope is configured on the workspace integration.
Tools
| 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('agent-memory', 'create_entities', {
workspaceId: '550e8400-e29b-41d4-a716-446655440000',
integrationAlias: 'agent-memory',
input: { /* ... */ },
})Related Integrations
Works well with
Frequently Asked Questions
How do I connect Agent Memory to my app?
Agent Memory does not require an external account connection. Install the SDK, add the integration to a workspace, then execute tools programmatically.
What tools does Agent Memory support?
Agent Memory supports 9 tools 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 Tool Mode or Code Mode. Code Mode provides 3 meta-tools with on-demand API discovery so agents can compose stateful workflows without loading every action schema up front.
Can Agent Memory be used in stateful agent workflows?
Yes. Agents can combine Agent Memory tools with Filesystem, State KV, Human Gates, input partials, and other workspace integrations while keeping execution scoped to the selected workspace or end user.
What authentication does Agent Memory use?
Agent Memory does not require external authentication.
How much does the Agent Memory integration cost?
The Agent Memory integration is included on all Weavz plans including the free tier with 20,000 actions per month. No credit card required.
Connect Agent Memory in minutes
Get 20,000 free action executions every month. No credit card required.