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

# Get the memory graph

> Returns active memories, extracted entities, and context documents as nodes, with
the edges between them. Chunk-level mention edges are rolled up to one weighted
document -> entity edge, so documents stay single nodes.




## OpenAPI

````yaml /openapi.yaml get /memory/graph
openapi: 3.1.0
info:
  title: memloom local API
  version: 0.1.0
  description: >
    The HTTP API served by the `memloom serve` daemon on your machine. The CLI,
    the MCP server,

    and the viewer all route through this API. The daemon is the single owner of
    the store, so

    every client shares one consistent view of your memories.


    No authentication: the daemon binds to `127.0.0.1` only and is reachable
    solely from your

    own machine. Browser clients on other localhost ports are allowed via CORS.
servers:
  - url: http://127.0.0.1:4319
    description: Local memloom daemon
security: []
paths:
  /memory/graph:
    get:
      summary: Get the memory graph
      description: >
        Returns active memories, extracted entities, and context documents as
        nodes, with

        the edges between them. Chunk-level mention edges are rolled up to one
        weighted

        document -> entity edge, so documents stay single nodes.
      operationId: getGraph
      responses:
        '200':
          description: The graph.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Graph'
components:
  schemas:
    Graph:
      type: object
      properties:
        memories:
          type: array
          items:
            type: object
            properties:
              id:
                type: string
              canonical:
                type: string
                nullable: true
              content:
                type: string
              memoryType:
                type: string
                enum:
                  - fact
                  - preference
                  - episode
                  - procedure
                example: fact
        entities:
          type: array
          items:
            type: object
            properties:
              id:
                type: string
              name:
                type: string
                example: Postgres
              entityType:
                type: string
                example: technology
        documents:
          type: array
          description: >-
            Ingested context documents. Chunk-level mentions roll up to these
            nodes.
          items:
            type: object
            properties:
              id:
                type: string
              title:
                type: string
                example: runbook.md
              path:
                type: string
                example: /home/me/docs/runbook.md
        edges:
          type: array
          items:
            type: object
            properties:
              from:
                type: string
              to:
                type: string
              relation:
                type: string
                example: mention
              weight:
                type: integer
                description: >-
                  On document -> entity edges, how many of the document's chunks
                  mention the entity.
                example: 3

````