H2O.ai · Schema

MemoryBlock

CompanyArtificial IntelligenceMachine LearningMLOpsGenerative AILLMRAGData ScienceModel DeploymentAI AgentsEnterprise AI

Properties

Name	Type	Description
id	string	Unique identifier of the memory block.
name	string	Name of the memory block.
content	string	Text content of the memory block.
system_prompt_amendment	string	System prompt amendment for agent mode.
injection_mode	string	Where memory content is injected. 'system_prompt' adds it to the LLM system prompt; 'user_instruction' prepends it to the user message; 'agent_file' makes it only available as AGENTS.md in agent mode;
access_mode	string	Controls whether the LLM/agent can read the memory, write to it, or both.
user_id	string	ID of the user who owns the memory block.
username	string	Username of the owner.
created_at	string	When the memory block was created.
updated_at	string	When the memory block was last updated.
is_public	boolean	Whether the memory block is publicly accessible.
is_owner	boolean	Whether the current user is the owner.
max_content_length	integer	Maximum number of characters allowed in memory content. 0 means unlimited.
is_auto	boolean	Whether this memory block was auto-created by the system for an AI assistant or chat session.
user_count	integer	The number of users the memory block has been directly shared with (excludes the owner).
group_count	integer	The number of groups the memory block has been shared with.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/h2o-ai/main/json-schema/h2o-ai-memory-block-schema.json",
  "title": "MemoryBlock",
  "x-generated": "2026-10-03",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/h2o-ai-memory-blocks-api-openapi.yml#/components/schemas/MemoryBlock",
  "type": "object",
  "required": [
    "id",
    "name",
    "content",
    "system_prompt_amendment",
    "injection_mode",
    "access_mode",
    "user_id",
    "created_at",
    "updated_at"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier of the memory block."
    },
    "name": {
      "type": "string",
      "description": "Name of the memory block."
    },
    "content": {
      "type": "string",
      "description": "Text content of the memory block."
    },
    "system_prompt_amendment": {
      "type": "string",
      "description": "System prompt amendment for agent mode."
    },
    "injection_mode": {
      "type": "string",
      "description": "Where memory content is injected. 'system_prompt' adds it to the LLM system prompt; 'user_instruction' prepends it to the user message; 'agent_file' makes it only available as AGENTS.md in agent mode; 'agent_tool' exposes content lazily via the read_memory_block / update_memory_block tools (no pre-injection).",
      "enum": [
        "system_prompt",
        "user_instruction",
        "agent_file",
        "agent_tool"
      ]
    },
    "access_mode": {
      "type": "string",
      "description": "Controls whether the LLM/agent can read the memory, write to it, or both.",
      "enum": [
        "read",
        "write",
        "read_write"
      ]
    },
    "user_id": {
      "type": "string",
      "description": "ID of the user who owns the memory block."
    },
    "username": {
      "type": "string",
      "description": "Username of the owner."
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "description": "When the memory block was created."
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
      "description": "When the memory block was last updated."
    },
    "is_public": {
      "type": "boolean",
      "description": "Whether the memory block is publicly accessible."
    },
    "is_owner": {
      "type": "boolean",
      "description": "Whether the current user is the owner."
    },
    "max_content_length": {
      "type": "integer",
      "description": "Maximum number of characters allowed in memory content. 0 means unlimited."
    },
    "is_auto": {
      "type": "boolean",
      "description": "Whether this memory block was auto-created by the system for an AI assistant or chat session."
    },
    "user_count": {
      "type": "integer",
      "description": "The number of users the memory block has been directly shared with (excludes the owner)."
    },
    "group_count": {
      "type": "integer",
      "description": "The number of groups the memory block has been shared with."
    }
  }
}

Work with this as data

Every JSON Schema 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 schemas

4 MCP tools reach this

find_json_schemasBrowse and filter every JSON Schema in the catalog.
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 JSON Schema

curl "https://apis.io/api/v1/json-schemas/h2o-ai-memory-block"

All schemas

curl "https://apis.io/api/v1/json-schemas?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.