Modify Agent

1 curl -X PATCH https://api.letta.com/v1/agents/ \ 2 -H "Authorization: Bearer <token>" \ 3 -H "Content-Type: application/json" \ 4 -d '{}'

1 { 2 "id": "foo", 3 "name": "foo", 4 "system": "foo", 5 "agent_type": "memgpt_agent", 6 "llm_config": { 7 "model": "foo", 8 "model_endpoint_type": "openai", 9 "context_window": 42, 10 "model_endpoint": "foo", 11 "provider_name": "foo", 12 "provider_category": "base", 13 "model_wrapper": "foo", 14 "put_inner_thoughts_in_kwargs": true, 15 "handle": "foo", 16 "temperature": 0.7, 17 "max_tokens": 42, 18 "enable_reasoner": false, 19 "reasoning_effort": "low", 20 "max_reasoning_tokens": 0 21 }, 22 "embedding_config": { 23 "embedding_endpoint_type": "openai", 24 "embedding_model": "foo", 25 "embedding_dim": 42, 26 "embedding_endpoint": "foo", 27 "embedding_chunk_size": 42, 28 "handle": "foo", 29 "azure_endpoint": "foo", 30 "azure_version": "foo", 31 "azure_deployment": "foo" 32 }, 33 "memory": { 34 "blocks": [ 35 { 36 "value": "foo", 37 "limit": 5000, 38 "name": "foo", 39 "is_template": false, 40 "preserve_on_migration": true, 41 "label": "foo", 42 "read_only": false, 43 "description": "foo", 44 "metadata": {}, 45 "id": "block-123e4567-e89b-12d3-a456-426614174000", 46 "created_by_id": "foo", 47 "last_updated_by_id": "foo" 48 } 49 ], 50 "file_blocks": [ 51 { 52 "value": "foo", 53 "limit": 5000, 54 "name": "foo", 55 "is_template": false, 56 "preserve_on_migration": true, 57 "label": "foo", 58 "read_only": false, 59 "description": "foo", 60 "metadata": {}, 61 "id": "block-123e4567-e89b-12d3-a456-426614174000", 62 "created_by_id": "foo", 63 "last_updated_by_id": "foo" 64 } 65 ], 66 "prompt_template": "{% for block in blocks %}<{{ block.label }}>\n<metadata>read_only=\"{{ block.read_only}}\" chars_current=\"{{ block.value|length }}\" chars_limit=\"{{ block.limit }}\"</metadata><value>{{ block.value }}\n</value></{{ block.label }}>\n{% if not loop.last %}\n{% endif %}{% endfor %}" 67 }, 68 "tools": [ 69 { 70 "id": "tool-123e4567-e89b-12d3-a456-426614174000", 71 "tool_type": "custom", 72 "description": "foo", 73 "source_type": "foo", 74 "name": "foo", 75 "tags": [ 76 "foo" 77 ], 78 "source_code": "foo", 79 "json_schema": {}, 80 "args_json_schema": {}, 81 "return_char_limit": 6000, 82 "pip_requirements": [ 83 { 84 "name": "foo", 85 "version": "foo" 86 } 87 ], 88 "created_by_id": "foo", 89 "last_updated_by_id": "foo", 90 "metadata_": {} 91 } 92 ], 93 "sources": [ 94 { 95 "name": "foo", 96 "embedding_config": { 97 "embedding_endpoint_type": "openai", 98 "embedding_model": "foo", 99 "embedding_dim": 42, 100 "embedding_endpoint": "foo", 101 "embedding_chunk_size": 42, 102 "handle": "foo", 103 "azure_endpoint": "foo", 104 "azure_version": "foo", 105 "azure_deployment": "foo" 106 }, 107 "id": "source-123e4567-e89b-12d3-a456-426614174000", 108 "description": "foo", 109 "instructions": "foo", 110 "metadata": {}, 111 "created_by_id": "foo", 112 "last_updated_by_id": "foo", 113 "created_at": "foo", 114 "updated_at": "foo" 115 } 116 ], 117 "tags": [ 118 "foo" 119 ], 120 "created_by_id": "foo", 121 "last_updated_by_id": "foo", 122 "created_at": "foo", 123 "updated_at": "foo", 124 "tool_rules": [ 125 { 126 "tool_name": "foo", 127 "type": "constrain_child_tools", 128 "prompt_template": "foo", 129 "children": [ 130 "foo" 131 ] 132 } 133 ], 134 "message_ids": [ 135 "foo" 136 ], 137 "response_format": { 138 "type": "text" 139 }, 140 "description": "foo", 141 "metadata": {}, 142 "tool_exec_environment_variables": [ 143 { 144 "key": "foo", 145 "value": "foo", 146 "agent_id": "foo", 147 "created_by_id": "foo", 148 "last_updated_by_id": "foo", 149 "created_at": "foo", 150 "updated_at": "foo", 151 "id": "agent-env-123e4567-e89b-12d3-a456-426614174000", 152 "description": "foo" 153 } 154 ], 155 "project_id": "foo", 156 "template_id": "foo", 157 "base_template_id": "foo", 158 "identity_ids": [ 159 "foo" 160 ], 161 "message_buffer_autoclear": false, 162 "enable_sleeptime": true, 163 "multi_agent_group": { 164 "id": "foo", 165 "manager_type": "round_robin", 166 "agent_ids": [ 167 "foo" 168 ], 169 "description": "foo", 170 "shared_block_ids": [ 171 "foo" 172 ], 173 "manager_agent_id": "foo", 174 "termination_token": "foo", 175 "max_turns": 42, 176 "sleeptime_agent_frequency": 42, 177 "turns_counter": 42, 178 "last_processed_message_id": "foo", 179 "max_message_buffer_length": 42, 180 "min_message_buffer_length": 42 181 } 182 }

Update an existing agent

Path parameters

agent_idstringRequired

Request

This endpoint expects an object.

namestringOptional

The name of the agent.

tool_idslist of stringsOptional

The ids of the tools used by the agent.

source_idslist of stringsOptional

The ids of the sources used by the agent.

block_idslist of stringsOptional

The ids of the blocks used by the agent.

tagslist of stringsOptional

The tags associated with the agent.

systemstringOptional

The system prompt used by the agent.

tool_ruleslist of objectsOptional

The tool rules governing the agent.

llm_configobjectOptional

The LLM configuration used by the agent.

embedding_configobjectOptional

The embedding configuration used by the agent.

message_idslist of stringsOptional

The ids of the messages in the agent’s in-context memory.

descriptionstringOptional

The description of the agent.

metadataobjectOptional

The metadata of the agent.

tool_exec_environment_variablesmap from strings to stringsOptional

The environment variables for tool execution specific to this agent.

project_idstringOptional

The id of the project the agent belongs to.

template_idstringOptional

The id of the template the agent belongs to.

base_template_idstringOptional

The base template id of the agent.

identity_idslist of stringsOptional

The ids of the identities associated with this agent.

message_buffer_autoclearbooleanOptional

If set to True, the agent will not remember previous messages (though the agent will still retain state via core memory blocks and archival/recall memory). Not recommended unless you have an advanced use case.

modelstringOptional

The LLM configuration handle used by the agent, specified in the format provider/model-name, as an alternative to specifying llm_config.

embeddingstringOptional

The embedding configuration handle used by the agent, specified in the format provider/model-name.

enable_sleeptimebooleanOptional

If set to True, memory management will move to a background agent thread.

response_formatobjectOptional

The response format for the agent.

Response

Successful Response

idstring

The id of the agent. Assigned by the database.

namestring

The name of the agent.

systemstring

The system prompt used by the agent.

agent_typeenum

The type of agent.

llm_configobject

The LLM configuration used by the agent.

embedding_configobject

The embedding configuration used by the agent.

memoryobject

The in-context memory of the agent.

toolslist of objects

The tools used by the agent.

sourceslist of objects

The sources used by the agent.

tagslist of strings

The tags associated with the agent.

created_by_idstring or null

The id of the user that made this object.

last_updated_by_idstring or null

The id of the user that made this object.

created_atstring or nullformat: "date-time"

The timestamp when the object was created.

updated_atstring or nullformat: "date-time"

The timestamp when the object was last updated.

tool_ruleslist of objects or null

The list of tool rules.

message_idslist of strings or null

The ids of the messages in the agent’s in-context memory.

response_formatobject or null

The response format used by the agent when returning from send_message.

descriptionstring or null

The description of the agent.

metadataobject or null

The metadata of the agent.

tool_exec_environment_variableslist of objects or null

The environment variables for tool execution specific to this agent.

project_idstring or null

The id of the project the agent belongs to.

template_idstring or null

The id of the template the agent belongs to.

base_template_idstring or null

The base template id of the agent.

identity_idslist of strings or null

The ids of the identities associated with this agent.

message_buffer_autoclearboolean or nullDefaults to false

enable_sleeptimeboolean or null

If set to True, memory management will move to a background agent thread.

multi_agent_groupobject or null

The multi-agent group that this agent manages

Path parameters

Headers

Request

Response