> ## Documentation Index
> Fetch the complete documentation index at: https://docs.niadra.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent memory tools

> `search_agent_memory` and `remember` as function definitions.



## OpenAPI

````yaml openapi/en/cell.json GET /v1/agent-memory/tools
openapi: 3.1.0
info:
  title: Niadra data API
  version: '1'
  description: >-
    Writing, context, history, objects, identity, privacy and governance of one
    space. Every space has a stable address, with the space and the region in
    its name.
servers:
  - url: https://{space}.{region}.api.niadra.com
    variables:
      space:
        default: acme-prod
        description: The space, which comes in the source key.
      region:
        default: us-east-2
        description: The region of the space, which also comes in the key.
security: []
paths:
  /v1/agent-memory/tools:
    get:
      tags:
        - agent-memory
      summary: Agent memory tools
      description: >-
        `search_agent_memory`, and `remember` when the key may write.


        **Authentication.** Source key with the `agent_memory` or `context`
        scope, or a Console person token with the `integration` role (or admin).
      operationId: tools_v1_agent_memory_tools_get
      responses:
        '200':
          content:
            application/json:
              schema:
                items:
                  $ref: '#/components/schemas/ToolDefinition'
                title: Response Tools V1 Agent Memory Tools Get
                type: array
          description: The definitions, in the same shape as `GET /v1/history/tools`.
      security:
        - sourceKey: []
        - personToken: []
      x-codeSamples:
        - lang: python
          label: Python
          source: >-
            # The history kit plus search_agent_memory (and remember, with
            write_agent_memory=True)

            kit = conversation.tools(agent_memory=True, write_agent_memory=True)

            reply = llm.chat.completions.create(model=MODEL, messages=messages,
            tools=kit.definitions)
        - lang: typescript
          label: TypeScript
          source: >-
            // The history kit plus search_agent_memory (and remember, with
            writeAgentMemory: true)

            const kit = conv.tools({ agentMemory: true, writeAgentMemory: true
            });

            const reply = await llm.chat.completions.create({ model: MODEL,
            messages, tools: kit.definitions });
components:
  schemas:
    ToolDefinition:
      additionalProperties: false
      description: A function-calling tool definition in the most common JSON Schema shape.
      properties:
        function:
          additionalProperties: true
          title: Function
          type: object
          description: '`name`, `description` and `parameters` (JSON Schema).'
        type:
          const: function
          default: function
          title: Type
          type: string
      required:
        - function
      title: ToolDefinition
      type: object
  securitySchemes:
    sourceKey:
      type: http
      scheme: bearer
      description: nia_sk_...
    personToken:
      type: http
      scheme: bearer
      bearerFormat: JWT

````