Create Agent Version - MemoryLake AI

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/agents/agt_r8k2m1n3/versions' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 25,
      "max_tool_calls": 15
    },
    "skills": [
      {
        "skill_id": "skl_kb_search",
        "skill_version": 3
      }
    ],
    "model_settings": {
      "temperature": 0.5,
      "max_tokens": 8192
    }
  }'

{
  "success": true,
  "data": {
    "version": 4,
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 25,
      "max_tool_calls": 15,
      "allow_tools": ["search_kb", "create_ticket"],
      "deny_tools": [],
      "subagent_timeout": 300,
      "subagent_max_concurrency": 3
    },
    "output": {
      "mode": "text",
      "json_schema": null
    },
    "subagents": [
      {
        "name": "ticket-creator",
        "mode": "delegate",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "skills": [
      {
        "skill_id": "skl_kb_search",
        "skill_version": 3
      }
    ],
    "agent_id": "agt_r8k2m1n3",
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.5,
      "max_tokens": 8192
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    },
    "created_at": "2025-05-15T10:00:00Z"
  }
}

POST /openapi/memorylake/api/v3/agents/{id}/versions

Creates a new version of the specified agent. The new version uses merge semantics: only the fields you supply override the previous version’s values. Omitted fields carry forward from the current version unchanged. This is how you update an agent’s model, capabilities, policies, subagents, skills, system prompt, and other configuration. The agent’s version field automatically advances to the newly created version.

Permission required: agent:version_create

Path Parameters

string

required

Agent identifier

Request Body

All fields are optional. Only supplied fields override the previous version.

string

Model to use for this version

array

Updated list of capability identifiers

object

Updated execution policies

Show Policies object

integer

Maximum number of conversation turns per run

integer

Maximum number of tool calls per turn

array

Allowlist of tool names the agent may invoke

array

Denylist of tool names the agent must not invoke

integer

Maximum seconds a subagent may run before being cancelled

integer

Maximum number of subagents that may run concurrently

object

Updated output configuration

Show Output object

string

Output mode (text or json)

object

JSON Schema that the agent’s output must conform to when mode is json

array

Updated subagent definitions

Show Subagent object

string

Subagent name

string

Execution mode for the subagent

string

Context instructions passed to the subagent

boolean

Whether the subagent inherits the parent agent’s tools

array

Updated skill references

Show Skill reference

string

Skill identifier

integer

Skill version number

string

Updated system prompt

object

Updated model-specific settings

object

Updated runtime binding configuration

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/agents/agt_r8k2m1n3/versions' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 25,
      "max_tool_calls": 15
    },
    "skills": [
      {
        "skill_id": "skl_kb_search",
        "skill_version": 3
      }
    ],
    "model_settings": {
      "temperature": 0.5,
      "max_tokens": 8192
    }
  }'

Response

object

Show Agent version object

integer

Version number of the newly created version

string

Model used in this version

array

List of capability identifiers

object

Execution policies for this version

Show Policies object

integer

Maximum number of conversation turns per run

integer

Maximum number of tool calls per turn

array

Allowlist of tool names the agent may invoke

array

Denylist of tool names the agent must not invoke

integer

Maximum seconds a subagent may run before being cancelled

integer

Maximum number of subagents that may run concurrently

object

Output configuration for this version

Show Output object

string

Output mode

object

JSON Schema for structured output

array

Subagent definitions in this version

Show Subagent object

string

Subagent name

string

Execution mode for the subagent

string

Context instructions passed to the subagent

boolean

Whether the subagent inherits the parent agent’s tools

array

Skills in this version

Show Skill reference

string

Skill identifier

integer

Skill version number

string

Parent agent identifier

string

System prompt used in this version

object

Model-specific settings for this version

object

Runtime binding configuration for this version

string

Version creation timestamp

{
  "success": true,
  "data": {
    "version": 4,
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 25,
      "max_tool_calls": 15,
      "allow_tools": ["search_kb", "create_ticket"],
      "deny_tools": [],
      "subagent_timeout": 300,
      "subagent_max_concurrency": 3
    },
    "output": {
      "mode": "text",
      "json_schema": null
    },
    "subagents": [
      {
        "name": "ticket-creator",
        "mode": "delegate",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "skills": [
      {
        "skill_id": "skl_kb_search",
        "skill_version": 3
      }
    ],
    "agent_id": "agt_r8k2m1n3",
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.5,
      "max_tokens": 8192
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    },
    "created_at": "2025-05-15T10:00:00Z"
  }
}

​Path Parameters

​Request Body

​Response

Path Parameters

Request Body

Response