hunta-ai

hunta-ai Memories API

The Memories API from hunta-ai — 4 operation(s) for memories.

GitHub OpenAPI

Operations 6

POST /v1/memories Store a memory (memory:write) #
GET /v1/memories List all memories in scope (memory:read) #
POST /v1/memories/search Filtered fact search (memory:read) #
GET /v1/memories/{mid} Get one memory (memory:read) #
DELETE /v1/memories/{mid} GDPR erasure — cascade delete (memory:write) #
POST /v1/memories/capture Stage a CANDIDATE memory — never recalled until promoted (memory:capture|write) #

Specifications

⚙
OpenAPI
https://artifacts.apis.io/hunta-ai/openapi/hunta-ai-memories-api-openapi.yml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/hunta-ai:hunta-ai-memories-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

hunta-ai-memories-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: hunta.ai Memory Memories API
  version: 0.17.0
  description: 'Attestable per-tenant agent memory. Tenant = the Bearer JWT''s `tid`; no endpoint takes a tenant argument. Scopes: memory:read|write|capture|curate|admin (legacy `memory` = read+write+capture+curate, not admin). Staging: capture → candidates (never recalled) → promote = the curated write into canon; promote/reject are provenance-stamped server-side (curated_by = token sub, lane = auto|human). Reconciliation (R0): facts listing + surgical supersede/invalidate (bi-temporal, curate-scope) + fact-granular forget (write-scope only).'
servers:
- url: https://mcp.hunta.ai
security:
- bearer: []
tags:
- name: Memories
paths:
  /v1/memories:
    post:
      summary: Store a memory (memory:write)
      requestBody:
        content:
          application/json:
            schema:
              type: object
              required:
              - text
              properties:
                text:
                  type: string
                agent:
                  type: string
                valid_from:
                  type: string
                  format: date-time
                  description: 'Event-time: when the fact became true (ISO-8601, not future). Extractor-inferred dates win.'
      responses:
        '201':
          description: created
        '401':
          description: unauthorized
        '403':
          description: insufficient_scope
      tags:
      - Memories
      operationId: postV1Memories
      x-operation-id-source: derived
    get:
      summary: List all memories in scope (memory:read)
      responses:
        '200':
          description: ok
      tags:
      - Memories
      operationId: getV1Memories
      x-operation-id-source: derived
  /v1/memories/search:
    post:
      summary: Filtered fact search (memory:read)
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                query:
                  type: string
                limit:
                  type: integer
                agent:
                  type: string
                as_of:
                  type: string
                  format: date-time
                entity:
                  type: string
      responses:
        '200':
          description: results with provenance
      tags:
      - Memories
      operationId: postV1MemoriesSearch
      x-operation-id-source: derived
  /v1/memories/{mid}:
    get:
      summary: Get one memory (memory:read)
      parameters:
      - name: mid
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: ok
        '404':
          description: not_found
      tags:
      - Memories
      operationId: getV1MemoriesByMid
      x-operation-id-source: derived
    delete:
      summary: GDPR erasure — cascade delete (memory:write)
      parameters:
      - name: mid
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: delete counts
      tags:
      - Memories
      operationId: deleteV1MemoriesByMid
      x-operation-id-source: derived
  /v1/memories/capture:
    post:
      summary: Stage a CANDIDATE memory — never recalled until promoted (memory:capture|write)
      requestBody:
        content:
          application/json:
            schema:
              type: object
              required:
              - text
              properties:
                text:
                  type: string
                agent:
                  type: string
                source:
                  type: string
                  description: api | hook_flush | gateway
      responses:
        '201':
          description: candidate created (or existing pending duplicate)
      tags:
      - Memories
      operationId: postV1MemoriesCapture
      x-operation-id-source: derived
components:
  securitySchemes:
    bearer:
      type: http
      scheme: bearer
      bearerFormat: JWT