Export Agent Serialized

1 curl https://api.letta.com/v1/agents/agent_id/export \ 2 -H "Authorization: Bearer <token>"

1 { 2 "agent_type": "agent_type", 3 "core_memory": [ 4 { 5 "created_at": "created_at", 6 "is_template": true, 7 "label": "label", 8 "limit": 1, 9 "updated_at": "updated_at", 10 "value": "value", 11 "description": "description", 12 "metadata_": { 13 "key": "value" 14 }, 15 "template_name": "template_name" 16 } 17 ], 18 "created_at": "created_at", 19 "embedding_config": { 20 "embedding_endpoint_type": "openai", 21 "embedding_model": "embedding_model", 22 "embedding_dim": 1, 23 "embedding_endpoint": "embedding_endpoint", 24 "embedding_chunk_size": 1, 25 "handle": "handle", 26 "azure_endpoint": "azure_endpoint", 27 "azure_version": "azure_version", 28 "azure_deployment": "azure_deployment" 29 }, 30 "llm_config": { 31 "model": "model", 32 "model_endpoint_type": "openai", 33 "context_window": 1, 34 "model_endpoint": "model_endpoint", 35 "model_wrapper": "model_wrapper", 36 "put_inner_thoughts_in_kwargs": true, 37 "handle": "handle", 38 "temperature": 1.1, 39 "max_tokens": 1, 40 "enable_reasoner": true, 41 "max_reasoning_tokens": 1 42 }, 43 "message_buffer_autoclear": true, 44 "in_context_message_indices": [ 45 1 46 ], 47 "messages": [ 48 { 49 "created_at": "created_at", 50 "role": "role", 51 "content": [ 52 { 53 "type": "text", 54 "text": "text" 55 } 56 ], 57 "tool_calls": [], 58 "tool_returns": [], 59 "updated_at": "updated_at", 60 "group_id": "group_id", 61 "model": "model", 62 "name": "name", 63 "tool_call_id": "tool_call_id" 64 } 65 ], 66 "multi_agent_group": { 67 "key": "value" 68 }, 69 "name": "name", 70 "system": "system", 71 "tags": [ 72 { 73 "tag": "tag" 74 } 75 ], 76 "tool_exec_environment_variables": [ 77 { 78 "created_at": "created_at", 79 "key": "key", 80 "updated_at": "updated_at", 81 "value": "value", 82 "description": "description" 83 } 84 ], 85 "tool_rules": [ 86 { 87 "tool_name": "tool_name", 88 "type": "type" 89 } 90 ], 91 "tools": [ 92 { 93 "args_json_schema": { 94 "key": "value" 95 }, 96 "created_at": "created_at", 97 "description": "description", 98 "json_schema": { 99 "name": "name", 100 "description": "description", 101 "parameters": { 102 "properties": { 103 "key": { 104 "type": "type" 105 } 106 } 107 } 108 }, 109 "name": "name", 110 "return_char_limit": 1, 111 "source_type": "source_type", 112 "tags": [ 113 "tags" 114 ], 115 "tool_type": "tool_type", 116 "updated_at": "updated_at", 117 "source_code": "source_code", 118 "metadata_": { 119 "key": "value" 120 } 121 } 122 ], 123 "updated_at": "updated_at", 124 "version": "version", 125 "description": "description", 126 "metadata_": { 127 "key": "value" 128 } 129 }

Export the serialized JSON representation of an agent.

Path parameters

agent_idstringRequired

Response

Successful Response

agent_typestring

core_memorylist of objects

created_atstring

embedding_configobject

Embedding model configuration. This object specifies all the information necessary to access an embedding model to usage with Letta, except for secret keys.

Attributes: embedding_endpoint_type (str): The endpoint type for the model. embedding_endpoint (str): The endpoint for the model. embedding_model (str): The model for the embedding. embedding_dim (int): The dimension of the embedding. embedding_chunk_size (int): The chunk size of the embedding. azure_endpoint (:obj:str, optional): The Azure endpoint for the model (Azure only). azure_version (str): The Azure version for the model (Azure only). azure_deployment (str): The Azure deployment for the model (Azure only).

llm_configobject

Configuration for a Language Model (LLM) model. This object specifies all the information necessary to access an LLM model to usage with Letta, except for secret keys.

Attributes: model (str): The name of the LLM model. model_endpoint_type (str): The endpoint type for the model. model_endpoint (str): The endpoint for the model. model_wrapper (str): The wrapper for the model. This is used to wrap additional text around the input/output of the model. This is useful for text-to-text completions, such as the Completions API in OpenAI. context_window (int): The context window size for the model. put_inner_thoughts_in_kwargs (bool): Puts inner_thoughts as a kwarg in the function call if this is set to True. This helps with function calling performance and also the generation of inner thoughts. temperature (float): The temperature to use when generating text with the model. A higher temperature will result in more random text. max_tokens (int): The maximum number of tokens to generate.

message_buffer_autoclearboolean

in_context_message_indiceslist of integers

messageslist of objects

multi_agent_groupany

namestring

systemstring

tagslist of objects

tool_exec_environment_variableslist of objects

tool_ruleslist of objects

toolslist of objects

updated_atstring

versionstring

descriptionstringOptional

metadata_map from strings to anyOptional

Export Agent Serialized

Path parameters

Headers

Response

Errors