Create Agent - MemoryLake AI

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/agents' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "Support Assistant",
    "custom_id": "support-assistant-v1",
    "description": "Handles customer support inquiries using knowledge base",
    "metadata": {
      "team": "customer-success",
      "tier": "production"
    },
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 20,
      "max_tool_calls": 10,
      "allow_tools": ["search_kb", "create_ticket"],
      "subagent_timeout": 300,
      "subagent_max_concurrency": 3
    },
    "output": {
      "mode": "text"
    },
    "subagents": [
      {
        "name": "ticket-creator",
        "mode": "fork",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.7,
      "max_tokens": 4096
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    }
  }'

{
  "success": true,
  "data": {
    "id": "agt_r8k2m1n3",
    "name": "Support Assistant",
    "description": "Handles customer support inquiries using knowledge base",
    "metadata": {
      "team": "customer-success",
      "tier": "production"
    },
    "version": 1,
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 20,
      "max_tool_calls": 10,
      "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": "fork",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "skills": [],
    "custom_id": "support-assistant-v1",
    "actor_id": "act_p4q7w2x9",
    "latest_version": 1,
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.7,
      "max_tokens": 4096
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    },
    "created_at": "2025-03-10T09:00:00Z",
    "updated_at": "2025-03-10T09:00:00Z"
  }
}

POST /openapi/memorylake/api/v3/agents

Creates a new agent with the specified configuration. You provide a name and custom identifier, and optionally attach a description, model, capabilities, policies, subagents, and other settings. The agent is created at version 1.

Permission required: agent:create

Request Body

name

string

required

Agent name

custom_id

string

required

Custom identifier for external system integration. Must be unique across your agents.

description

string

Agent description

metadata

object

Arbitrary key-value pairs for storing additional agent information

model

string

Model to use for the agent (e.g. gpt-4o, claude-sonnet-4-20250514)

capabilities

array

List of capability identifiers the agent supports (e.g. tool_use, memory_read, memory_write)

policies

object

Execution policies that constrain agent behavior

Show Policies object

policies.max_turns

integer

Maximum number of conversation turns per run

policies.max_tool_calls

integer

Maximum number of tool calls per turn

policies.allow_tools

array

Allowlist of tool names the agent may invoke

policies.deny_tools

array

Denylist of tool names the agent must not invoke

policies.subagent_timeout

integer

Maximum seconds a subagent may run before being cancelled

policies.subagent_max_concurrency

integer

Maximum number of subagents that may run concurrently

output

object

Output configuration for the agent

Show Output object

output.mode

string

Output mode (text or json)

output.json_schema

object

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

subagents

array

Subagent definitions to attach to this agent

Show Subagent object

subagents[].name

string

Subagent name

subagents[].mode

string

Execution mode: fork or swarm

subagents[].context

string

Context instructions passed to the subagent

subagents[].inherit_tools

boolean

Whether the subagent inherits the parent agent’s tools

system_prompt

string

System prompt used to instruct the agent

model_settings

object

Model-specific settings such as temperature and max tokens

runtime_bindings

object

Runtime binding configuration for tools and data sources

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v3/agents' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "Support Assistant",
    "custom_id": "support-assistant-v1",
    "description": "Handles customer support inquiries using knowledge base",
    "metadata": {
      "team": "customer-success",
      "tier": "production"
    },
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 20,
      "max_tool_calls": 10,
      "allow_tools": ["search_kb", "create_ticket"],
      "subagent_timeout": 300,
      "subagent_max_concurrency": 3
    },
    "output": {
      "mode": "text"
    },
    "subagents": [
      {
        "name": "ticket-creator",
        "mode": "fork",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.7,
      "max_tokens": 4096
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    }
  }'

Response

data

object

Show Agent object

string

Unique agent identifier

name

string

Agent name

description

string

Agent description

metadata

object

Arbitrary key-value pairs for storing additional agent information

version

integer

Current active version number

model

string

Model used by the agent

capabilities

array

List of capability identifiers the agent supports

policies

object

Execution policies that constrain agent behavior

Show Policies object

max_turns

integer

Maximum number of conversation turns per run

max_tool_calls

integer

Maximum number of tool calls per turn

allow_tools

array

Allowlist of tool names the agent may invoke

deny_tools

array

Denylist of tool names the agent must not invoke

subagent_timeout

integer

Maximum seconds a subagent may run before being cancelled

subagent_max_concurrency

integer

Maximum number of subagents that may run concurrently

output

object

Output configuration for the agent

Show Output object

mode

string

Output mode

json_schema

object

JSON Schema for structured output

subagents

array

Subagent definitions attached to this agent

Show Subagent object

name

string

Subagent name

mode

string

Execution mode: fork or swarm

context

string

Context instructions passed to the subagent

inherit_tools

boolean

Whether the subagent inherits the parent agent’s tools

skills

array

Skills attached to this agent

Show Skill reference

skill_id

string

Skill identifier

skill_version

integer

Skill version number

custom_id

string

Custom identifier for external system integration

actor_id

string

Actor identifier associated with this agent

latest_version

integer

Latest version number available for this agent

system_prompt

string

System prompt used to instruct the agent

model_settings

object

Model-specific settings such as temperature and max tokens

runtime_bindings

object

Runtime binding configuration for tools and data sources

created_at

string

Creation timestamp

updated_at

string

Last update timestamp

{
  "success": true,
  "data": {
    "id": "agt_r8k2m1n3",
    "name": "Support Assistant",
    "description": "Handles customer support inquiries using knowledge base",
    "metadata": {
      "team": "customer-success",
      "tier": "production"
    },
    "version": 1,
    "model": "gpt-4o",
    "capabilities": ["tool_use", "memory_read", "memory_write"],
    "policies": {
      "max_turns": 20,
      "max_tool_calls": 10,
      "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": "fork",
        "context": "Create support tickets from conversation context",
        "inherit_tools": false
      }
    ],
    "skills": [],
    "custom_id": "support-assistant-v1",
    "actor_id": "act_p4q7w2x9",
    "latest_version": 1,
    "system_prompt": "You are a helpful support assistant. Use the knowledge base to answer questions accurately.",
    "model_settings": {
      "temperature": 0.7,
      "max_tokens": 4096
    },
    "runtime_bindings": {
      "knowledge_base": "kb_prod_docs"
    },
    "created_at": "2025-03-10T09:00:00Z",
    "updated_at": "2025-03-10T09:00:00Z"
  }
}

List Agents Get Agent

​Request Body

​Response

Request Body

Response