robosystems-ai Memory API

openapi: 3.2.0
info:
  title: RoboSystems Memory API
  description: 'The REST and GraphQL API for RoboSystems — an open-source, AI-native platform for accounting, financial reporting and investment management. It powers RoboLedger and RoboInvestor.


    ## Two surfaces


    **Platform** — `/v1/…` — graphs, queries, schema, documents, search, memory, connections, billing and access. Reads are REST `GET`s; every write is a named operation at `/operations/{name}` returning an `OperationEnvelope`, accepting an `Idempotency-Key`, and streaming progress at `/v1/operations/{id}/stream`.

    → API reference


    **Extensions** — `/extensions/…` — RoboLedger and RoboInvestor, scoped by `graph_id` in the URL. Reads are GraphQL at `POST /extensions/{graph_id}/graphql` and change nothing; writes are named operations at `/extensions/{domain}/{graph_id}/operations/{name}`; analytical views read the materialized graph.

    → Extensions reference · every GraphQL query


    ## Authenticating


    `X-API-Key: rfs…` on REST, GraphQL and per-graph MCP. Browser sessions use JWTs from `POST /v1/auth/login`. The graph-agnostic MCP endpoint `/v1/mcp` takes OAuth 2.1 bearer tokens only.


    ## Connecting an AI client


    Every graph is an MCP server at `POST /v1/graphs/{graph_id}/mcp`, and `POST /v1/mcp` serves OAuth clients that pick their graph at consent.

    → MCP guide


    ## Clients


    `robosystems-client` for Python, `@robosystems/client` for TypeScript.

    → Guides · Technical docs'
  version: 1.20.6
tags:
- name: Memory
  description: 🧠 Memory - Recall, list, and inspect the graph's per-graph semantic memory store
paths:
  /v1/graphs/{graph_id}/memory:
    get:
      tags:
      - Memory
      summary: List Memories
      operationId: listMemories
      security:
      - APIKeyHeader: []
      - BearerAuth: []
      parameters:
      - name: graph_id
        in: path
        required: true
        schema:
          type: string
          title: Graph Id
      - name: memory_type
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by memory type
          title: Memory Type
        description: Filter by memory type
      - name: source
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by source
          title: Source
        description: Filter by source
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          maximum: 500
          minimum: 1
          default: 100
          title: Limit
      - name: offset
        in: query
        required: false
        schema:
          type: integer
          minimum: 0
          default: 0
          title: Offset
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MemoryListResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication required
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Access denied
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Resource not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/graphs/{graph_id}/memory/{memory_id}:
    get:
      tags:
      - Memory
      summary: Get Memory
      operationId: getMemory
      security:
      - APIKeyHeader: []
      - BearerAuth: []
      parameters:
      - name: graph_id
        in: path
        required: true
        schema:
          type: string
          title: Graph Id
      - name: memory_id
        in: path
        required: true
        schema:
          type: string
          pattern: ^mem_[0-9a-f]{32}$
          title: Memory Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MemoryRecord'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication required
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Access denied
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Resource not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/graphs/{graph_id}/memory/recall:
    post:
      tags:
      - Memory
      summary: Recall Semantic Memory
      description: Ranked semantic recall over the graph's per-graph memory store. Returns scored hits in the same shape as document search.
      operationId: recallMemory
      security:
      - APIKeyHeader: []
      - BearerAuth: []
      parameters:
      - name: graph_id
        in: path
        required: true
        schema:
          type: string
          title: Graph Id
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MemoryRecallRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SearchResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Rate limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Authentication required
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Access denied
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Resource not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '503':
          description: Semantic memory not available
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    MemoryRecord:
      properties:
        id:
          type: string
          title: Id
        text:
          type: string
          title: Text
        source:
          anyOf:
          - type: string
          - type: 'null'
          title: Source
        memory_type:
          anyOf:
          - type: string
          - type: 'null'
          title: Memory Type
        tags:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Tags
        source_ref:
          anyOf:
          - type: string
          - type: 'null'
          title: Source Ref
        provenance:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Provenance
        created_by:
          anyOf:
          - type: string
          - type: 'null'
          title: Created By
        created_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Created At
        updated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Updated At
      type: object
      required:
      - id
      - text
      title: MemoryRecord
      description: A stored memory (never includes the raw embedding vector).
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    MemoryListResponse:
      properties:
        total:
          type: integer
          title: Total
        memories:
          items:
            $ref: '#/components/schemas/MemoryRecord'
          type: array
          title: Memories
        graph_id:
          type: string
          title: Graph Id
      type: object
      required:
      - total
      - memories
      - graph_id
      title: MemoryListResponse
      description: Governance list of memories for a graph.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ErrorResponse:
      properties:
        detail:
          type: string
          title: Detail
          description: Human-readable error message explaining what went wrong
          examples:
          - Insufficient credits for operation
        code:
          anyOf:
          - type: string
          - type: 'null'
          title: Code
          description: Machine-readable error code for programmatic handling
          examples:
          - INSUFFICIENT_CREDITS
        request_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Request Id
          description: Unique request ID for tracking and debugging
          examples:
          - req_1234567890abcdef
        timestamp:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Timestamp
          description: Timestamp when the error occurred
          examples:
          - '2024-01-01T00:00:00Z'
      type: object
      required:
      - detail
      title: ErrorResponse
      description: Error body returned by every endpoint.
      example:
        code: RESOURCE_NOT_FOUND
        detail: Resource not found
        request_id: req_1234567890abcdef
        timestamp: '2024-01-01T00:00:00Z'
    MemoryRecallRequest:
      properties:
        query:
          type: string
          maxLength: 500
          minLength: 1
          title: Query
          description: Recall query
        k:
          type: integer
          maximum: 50.0
          minimum: 1.0
          title: K
          description: Max results to return
          default: 10
        memory_type:
          anyOf:
          - type: string
          - type: 'null'
          title: Memory Type
          description: Filter by memory type
        source:
          anyOf:
          - type: string
          - type: 'null'
          title: Source
          description: Filter by source
      type: object
      required:
      - query
      title: MemoryRecallRequest
      description: Body for recall (ranked semantic search over memory).
    SearchHit:
      properties:
        document_id:
          type: string
          title: Document Id
        score:
          type: number
          title: Score
        source_type:
          type: string
          title: Source Type
        parent_document_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Parent Document Id
        part:
          type: integer
          title: Part
          default: 1
        part_count:
          type: integer
          title: Part Count
          default: 1
        next_document_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Next Document Id
        entity_ticker:
          anyOf:
          - type: string
          - type: 'null'
          title: Entity Ticker
        entity_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Entity Name
        section_label:
          anyOf:
          - type: string
          - type: 'null'
          title: Section Label
        section_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Section Id
        element_qname:
          anyOf:
          - type: string
          - type: 'null'
          title: Element Qname
        filing_date:
          anyOf:
          - type: string
          - type: 'null'
          title: Filing Date
        fiscal_year:
          anyOf:
          - type: integer
          - type: 'null'
          title: Fiscal Year
        form_type:
          anyOf:
          - type: string
          - type: 'null'
          title: Form Type
        accession_number:
          anyOf:
          - type: string
          - type: 'null'
          title: Accession Number
        xbrl_elements:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Xbrl Elements
        snippet:
          type: string
          title: Snippet
        content_length:
          type: integer
          title: Content Length
          default: 0
        content_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Content Url
        document_title:
          anyOf:
          - type: string
          - type: 'null'
          title: Document Title
        tags:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Tags
        folder:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder
        also_in_filings:
          anyOf:
          - type: integer
          - type: 'null'
          title: Also In Filings
      type: object
      required:
      - document_id
      - score
      - source_type
      - snippet
      title: SearchHit
      description: 'A single search result with snippet.


        A long SEC section (an MD&A, a commitments note) is indexed in parts, each

        a document of its own: `part` of `part_count`, `parent_document_id`

        shared by the section''s parts, `next_document_id` to read on.


        On a grouped search, `also_in_filings` counts the other filings of the

        same filer whose same section (and part) matched and were folded into

        this hit.'
    SearchResponse:
      properties:
        total:
          type: integer
          title: Total
          description: Matching documents before any grouping, as OpenSearch counts them (it stops counting at 10,000). Not the number of distinct results a grouped search can page through.
        hits:
          items:
            $ref: '#/components/schemas/SearchHit'
          type: array
          title: Hits
        query:
          type: string
          title: Query
        graph_id:
          type: string
          title: Graph Id
      type: object
      required:
      - total
      - hits
      - query
      - graph_id
      title: SearchResponse
      description: Response model for document search.
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key
      description: API key for authentication
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: JWT bearer token