Skip to main content
POST
/
sandbox
/
mem0
/
{sandbox_id}
/
initialize
Initialize mem0 sandbox with data
curl --request POST \
  --url https://api.klavis.ai/sandbox/mem0/{sandbox_id}/initialize \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "memory_list": [
    {
      "message_list": [
        {
          "role": "user",
          "content": "I prefer dark mode for all applications"
        }
      ],
      "user_id": "user_001",
      "agent_id": "agent_assistant",
      "app_id": "settings_app",
      "run_id": "run_12345",
      "auto_infer": true,
      "background_processing": true,
      "category_definitions": [
        {
          "ui_preferences": "Tracks user interface settings and visual preferences including themes, colors, and display options"
        }
      ],
      "metadata": {
        "category": "preferences",
        "tags": [
          "ui",
          "settings"
        ]
      },
      "version": "v2"
    },
    {
      "message_list": [
        {
          "role": "user",
          "content": "My favorite programming language is Python"
        },
        {
          "role": "assistant",
          "content": "I've noted that Python is your favorite programming language."
        }
      ],
      "user_id": "user_001",
      "agent_id": "agent_assistant",
      "app_id": "dev_app",
      "run_id": "run_12346",
      "auto_infer": true,
      "background_processing": true,
      "category_definitions": [
        {
          "technical_skills": "Tracks programming languages, frameworks, tools and technical expertise levels"
        }
      ],
      "metadata": {
        "category": "preferences",
        "tags": [
          "programming",
          "development"
        ]
      },
      "version": "v2"
    },
    {
      "message_list": [
        {
          "role": "user",
          "content": "I have a meeting every Monday at 9 AM"
        }
      ],
      "user_id": "user_001",
      "agent_id": "agent_calendar",
      "app_id": "calendar_app",
      "run_id": "run_12347",
      "auto_infer": true,
      "background_processing": false,
      "category_definitions": [
        {
          "schedule_management": "Tracks recurring events, meetings, appointments and time commitments"
        }
      ],
      "processing_instructions": "Store all calendar events with timezone information",
      "metadata": {
        "category": "schedule",
        "tags": [
          "calendar",
          "recurring"
        ]
      },
      "version": "v2"
    },
    {
      "message_list": [
        {
          "role": "user",
          "content": "I'm working on a machine learning project using TensorFlow"
        }
      ],
      "user_id": "user_001",
      "agent_id": "agent_assistant",
      "app_id": "project_app",
      "run_id": "run_12348",
      "auto_infer": true,
      "background_processing": true,
      "include_preferences": "project details, technologies, status",
      "category_definitions": [
        {
          "project_tracking": "Tracks active and past projects including technologies used, status, and objectives"
        }
      ],
      "metadata": {
        "category": "projects",
        "tags": [
          "ml",
          "tensorflow",
          "current"
        ]
      },
      "version": "v2"
    },
    {
      "message_list": [
        {
          "role": "user",
          "content": "My email is user@example.com"
        }
      ],
      "user_id": "user_001",
      "agent_id": "agent_assistant",
      "app_id": "contact_app",
      "run_id": "run_12349",
      "auto_infer": false,
      "background_processing": true,
      "read_only": true,
      "exclude_preferences": "temporary contact info",
      "category_definitions": [
        {
          "contact_information": "Tracks permanent contact details including email, phone numbers, and social media handles"
        }
      ],
      "metadata": {
        "category": "contact",
        "tags": [
          "email",
          "personal"
        ]
      },
      "version": "v2"
    }
  ]
}
EOF
import requests

url = "https://api.klavis.ai/sandbox/mem0/{sandbox_id}/initialize"

payload = { "memory_list": [
        {
            "message_list": [
                {
                    "role": "user",
                    "content": "I prefer dark mode for all applications"
                }
            ],
            "user_id": "user_001",
            "agent_id": "agent_assistant",
            "app_id": "settings_app",
            "run_id": "run_12345",
            "auto_infer": True,
            "background_processing": True,
            "category_definitions": [{ "ui_preferences": "Tracks user interface settings and visual preferences including themes, colors, and display options" }],
            "metadata": {
                "category": "preferences",
                "tags": ["ui", "settings"]
            },
            "version": "v2"
        },
        {
            "message_list": [
                {
                    "role": "user",
                    "content": "My favorite programming language is Python"
                },
                {
                    "role": "assistant",
                    "content": "I've noted that Python is your favorite programming language."
                }
            ],
            "user_id": "user_001",
            "agent_id": "agent_assistant",
            "app_id": "dev_app",
            "run_id": "run_12346",
            "auto_infer": True,
            "background_processing": True,
            "category_definitions": [{ "technical_skills": "Tracks programming languages, frameworks, tools and technical expertise levels" }],
            "metadata": {
                "category": "preferences",
                "tags": ["programming", "development"]
            },
            "version": "v2"
        },
        {
            "message_list": [
                {
                    "role": "user",
                    "content": "I have a meeting every Monday at 9 AM"
                }
            ],
            "user_id": "user_001",
            "agent_id": "agent_calendar",
            "app_id": "calendar_app",
            "run_id": "run_12347",
            "auto_infer": True,
            "background_processing": False,
            "category_definitions": [{ "schedule_management": "Tracks recurring events, meetings, appointments and time commitments" }],
            "processing_instructions": "Store all calendar events with timezone information",
            "metadata": {
                "category": "schedule",
                "tags": ["calendar", "recurring"]
            },
            "version": "v2"
        },
        {
            "message_list": [
                {
                    "role": "user",
                    "content": "I'm working on a machine learning project using TensorFlow"
                }
            ],
            "user_id": "user_001",
            "agent_id": "agent_assistant",
            "app_id": "project_app",
            "run_id": "run_12348",
            "auto_infer": True,
            "background_processing": True,
            "include_preferences": "project details, technologies, status",
            "category_definitions": [{ "project_tracking": "Tracks active and past projects including technologies used, status, and objectives" }],
            "metadata": {
                "category": "projects",
                "tags": ["ml", "tensorflow", "current"]
            },
            "version": "v2"
        },
        {
            "message_list": [
                {
                    "role": "user",
                    "content": "My email is user@example.com"
                }
            ],
            "user_id": "user_001",
            "agent_id": "agent_assistant",
            "app_id": "contact_app",
            "run_id": "run_12349",
            "auto_infer": False,
            "background_processing": True,
            "read_only": True,
            "exclude_preferences": "temporary contact info",
            "category_definitions": [{ "contact_information": "Tracks permanent contact details including email, phone numbers, and social media handles" }],
            "metadata": {
                "category": "contact",
                "tags": ["email", "personal"]
            },
            "version": "v2"
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    memory_list: [
      {
        message_list: [{role: 'user', content: 'I prefer dark mode for all applications'}],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'settings_app',
        run_id: 'run_12345',
        auto_infer: true,
        background_processing: true,
        category_definitions: [
          {
            ui_preferences: 'Tracks user interface settings and visual preferences including themes, colors, and display options'
          }
        ],
        metadata: {category: 'preferences', tags: ['ui', 'settings']},
        version: 'v2'
      },
      {
        message_list: [
          {role: 'user', content: 'My favorite programming language is Python'},
          {
            role: 'assistant',
            content: 'I\'ve noted that Python is your favorite programming language.'
          }
        ],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'dev_app',
        run_id: 'run_12346',
        auto_infer: true,
        background_processing: true,
        category_definitions: [
          {
            technical_skills: 'Tracks programming languages, frameworks, tools and technical expertise levels'
          }
        ],
        metadata: {category: 'preferences', tags: ['programming', 'development']},
        version: 'v2'
      },
      {
        message_list: [{role: 'user', content: 'I have a meeting every Monday at 9 AM'}],
        user_id: 'user_001',
        agent_id: 'agent_calendar',
        app_id: 'calendar_app',
        run_id: 'run_12347',
        auto_infer: true,
        background_processing: false,
        category_definitions: [
          {
            schedule_management: 'Tracks recurring events, meetings, appointments and time commitments'
          }
        ],
        processing_instructions: 'Store all calendar events with timezone information',
        metadata: {category: 'schedule', tags: ['calendar', 'recurring']},
        version: 'v2'
      },
      {
        message_list: [
          {
            role: 'user',
            content: 'I\'m working on a machine learning project using TensorFlow'
          }
        ],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'project_app',
        run_id: 'run_12348',
        auto_infer: true,
        background_processing: true,
        include_preferences: 'project details, technologies, status',
        category_definitions: [
          {
            project_tracking: 'Tracks active and past projects including technologies used, status, and objectives'
          }
        ],
        metadata: {category: 'projects', tags: ['ml', 'tensorflow', 'current']},
        version: 'v2'
      },
      {
        message_list: [{role: 'user', content: 'My email is user@example.com'}],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'contact_app',
        run_id: 'run_12349',
        auto_infer: false,
        background_processing: true,
        read_only: true,
        exclude_preferences: 'temporary contact info',
        category_definitions: [
          {
            contact_information: 'Tracks permanent contact details including email, phone numbers, and social media handles'
          }
        ],
        metadata: {category: 'contact', tags: ['email', 'personal']},
        version: 'v2'
      }
    ]
  })
};

fetch('https://api.klavis.ai/sandbox/mem0/{sandbox_id}/initialize', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    memory_list: [
      {
        message_list: [{role: 'user', content: 'I prefer dark mode for all applications'}],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'settings_app',
        run_id: 'run_12345',
        auto_infer: true,
        background_processing: true,
        category_definitions: [
          {
            ui_preferences: 'Tracks user interface settings and visual preferences including themes, colors, and display options'
          }
        ],
        metadata: {category: 'preferences', tags: ['ui', 'settings']},
        version: 'v2'
      },
      {
        message_list: [
          {role: 'user', content: 'My favorite programming language is Python'},
          {
            role: 'assistant',
            content: 'I\'ve noted that Python is your favorite programming language.'
          }
        ],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'dev_app',
        run_id: 'run_12346',
        auto_infer: true,
        background_processing: true,
        category_definitions: [
          {
            technical_skills: 'Tracks programming languages, frameworks, tools and technical expertise levels'
          }
        ],
        metadata: {category: 'preferences', tags: ['programming', 'development']},
        version: 'v2'
      },
      {
        message_list: [{role: 'user', content: 'I have a meeting every Monday at 9 AM'}],
        user_id: 'user_001',
        agent_id: 'agent_calendar',
        app_id: 'calendar_app',
        run_id: 'run_12347',
        auto_infer: true,
        background_processing: false,
        category_definitions: [
          {
            schedule_management: 'Tracks recurring events, meetings, appointments and time commitments'
          }
        ],
        processing_instructions: 'Store all calendar events with timezone information',
        metadata: {category: 'schedule', tags: ['calendar', 'recurring']},
        version: 'v2'
      },
      {
        message_list: [
          {
            role: 'user',
            content: 'I\'m working on a machine learning project using TensorFlow'
          }
        ],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'project_app',
        run_id: 'run_12348',
        auto_infer: true,
        background_processing: true,
        include_preferences: 'project details, technologies, status',
        category_definitions: [
          {
            project_tracking: 'Tracks active and past projects including technologies used, status, and objectives'
          }
        ],
        metadata: {category: 'projects', tags: ['ml', 'tensorflow', 'current']},
        version: 'v2'
      },
      {
        message_list: [{role: 'user', content: 'My email is user@example.com'}],
        user_id: 'user_001',
        agent_id: 'agent_assistant',
        app_id: 'contact_app',
        run_id: 'run_12349',
        auto_infer: false,
        background_processing: true,
        read_only: true,
        exclude_preferences: 'temporary contact info',
        category_definitions: [
          {
            contact_information: 'Tracks permanent contact details including email, phone numbers, and social media handles'
          }
        ],
        metadata: {category: 'contact', tags: ['email', 'personal']},
        version: 'v2'
      }
    ]
  })
};

fetch('https://api.klavis.ai/sandbox/mem0/{sandbox_id}/initialize', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
{
  "sandbox_id": "<string>",
  "message": "<string>"
}
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Your Klavis AI API key.

Path Parameters

​
sandbox_id
string
required

The unique sandbox identifier

Query Parameters

​
init_default_data
boolean
default:false

If true, use default test data for initialization

Body

application/json

Complete Mem0 sandbox data structure

​
memory_list
Mem0Memory · object[]

List of memories

Response

Successful Response

Response model for sandbox initialization

​
sandbox_id
string
required

Sandbox identifier

​
status
enum<string>
required

Current status

Available options:
idle,
occupied,
error
​
message
string
required

Initialization result message