Create Agent — Letta

Create a new agent with the specified configuration.

Request

This endpoint expects an object.

namestringOptional

The name of the agent.

memory_blockslist of objectsOptional

The blocks to create in the agent’s in-context memory.

toolslist of stringsOptional

The tools used by 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.

tool_ruleslist of objectsOptional

The tool rules governing the agent.

tagslist of stringsOptional

The tags associated with the agent.

systemstringOptional

The system prompt used by the agent.

agent_typeenumOptional

Allowed values: memgpt_agentsplit_thread_agentoffline_memory_agentchat_only_agent

The type of agent.

llm_configobjectOptional

The LLM configuration used by the agent.

embedding_configobjectOptional

The embedding configuration used by the agent.

initial_message_sequencelist of objectsOptional

The initial set of messages to put in the agent’s in-context memory.

include_base_toolsbooleanOptionalDefaults to true

If true, attaches the Letta core tools (e.g. archival_memory and core_memory related functions).

include_multi_agent_toolsbooleanOptionalDefaults to false

If true, attaches the Letta multi-agent tools (e.g. sending a message to another agent).

descriptionstringOptional

The description of the agent.

metadatamap from strings to anyOptional

The metadata of the agent.

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.

context_window_limitintegerOptional

The context window limit used by the agent.

embedding_chunk_sizeintegerOptional

The embedding chunk size used by the agent.

from_templatestringOptional

The template id used to configure the agent

templatebooleanOptionalDefaults to false

Whether the agent is a template

projectstringOptional

The project slug that the agent will be associated with.

tool_exec_environment_variablesmap from strings to optional stringsOptional

The environment variables for tool execution specific to this agent.

memory_variablesmap from strings to optional stringsOptional

The variables that should be set 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

Allowed values: memgpt_agentsplit_thread_agentoffline_memory_agentchat_only_agent

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_idstringOptional

The id of the user that made this object.

last_updated_by_idstringOptional

The id of the user that made this object.

created_atdatetimeOptional

The timestamp when the object was created.

updated_atdatetimeOptional

The timestamp when the object was last updated.

tool_ruleslist of objectsOptional

The list of tool rules.

message_idslist of stringsOptional

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

descriptionstringOptional

The description of the agent.

metadatamap from strings to anyOptional

The metadata of the agent.

tool_exec_environment_variableslist of objectsOptional

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.

Errors

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

1 { 2 "id": "id", 3 "name": "name", 4 "system": "system", 5 "agent_type": "memgpt_agent", 6 "llm_config": { 7 "model": "model", 8 "model_endpoint_type": "openai", 9 "context_window": 1, 10 "model_endpoint": "model_endpoint", 11 "model_wrapper": "model_wrapper", 12 "put_inner_thoughts_in_kwargs": true, 13 "handle": "handle", 14 "temperature": 1.1 15 }, 16 "embedding_config": { 17 "embedding_endpoint_type": "openai", 18 "embedding_model": "embedding_model", 19 "embedding_dim": 1, 20 "embedding_endpoint": "embedding_endpoint", 21 "embedding_chunk_size": 1, 22 "handle": "handle", 23 "azure_endpoint": "azure_endpoint", 24 "azure_version": "azure_version", 25 "azure_deployment": "azure_deployment" 26 }, 27 "memory": { 28 "blocks": [ 29 { 30 "value": "value", 31 "id": "block-123e4567-e89b-12d3-a456-426614174000" 32 } 33 ], 34 "prompt_template": "prompt_template" 35 }, 36 "tools": [ 37 { 38 "id": "tool-123e4567-e89b-12d3-a456-426614174000", 39 "tool_type": "custom", 40 "description": "description", 41 "source_type": "source_type", 42 "name": "name", 43 "tags": [ 44 "tags" 45 ], 46 "source_code": "source_code", 47 "json_schema": { 48 "key": "value" 49 }, 50 "return_char_limit": 1, 51 "created_by_id": "created_by_id", 52 "last_updated_by_id": "last_updated_by_id" 53 } 54 ], 55 "sources": [ 56 { 57 "name": "name", 58 "embedding_config": { 59 "embedding_endpoint_type": "openai", 60 "embedding_model": "embedding_model", 61 "embedding_dim": 1 62 }, 63 "id": "source-123e4567-e89b-12d3-a456-426614174000", 64 "description": "description", 65 "metadata": { 66 "key": "value" 67 }, 68 "created_by_id": "created_by_id", 69 "last_updated_by_id": "last_updated_by_id", 70 "created_at": "2024-01-15T09:30:00Z", 71 "updated_at": "2024-01-15T09:30:00Z" 72 } 73 ], 74 "tags": [ 75 "tags" 76 ], 77 "created_by_id": "created_by_id", 78 "last_updated_by_id": "last_updated_by_id", 79 "created_at": "2024-01-15T09:30:00Z", 80 "updated_at": "2024-01-15T09:30:00Z", 81 "tool_rules": [ 82 { 83 "tool_name": "tool_name", 84 "type": "conditional", 85 "default_child": "default_child", 86 "child_output_mapping": { 87 "key": "value" 88 }, 89 "require_output_mapping": true 90 } 91 ], 92 "message_ids": [ 93 "message_ids" 94 ], 95 "description": "description", 96 "metadata": { 97 "key": "value" 98 }, 99 "tool_exec_environment_variables": [ 100 { 101 "key": "key", 102 "value": "value", 103 "agent_id": "agent_id", 104 "created_by_id": "created_by_id", 105 "last_updated_by_id": "last_updated_by_id", 106 "created_at": "2024-01-15T09:30:00Z", 107 "updated_at": "2024-01-15T09:30:00Z", 108 "id": "agent-env-123e4567-e89b-12d3-a456-426614174000", 109 "description": "description" 110 } 111 ], 112 "project_id": "project_id", 113 "template_id": "template_id", 114 "base_template_id": "base_template_id" 115 }

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

1	{
2	"id": "id",
3	"name": "name",
4	"system": "system",
5	"agent_type": "memgpt_agent",
6	"llm_config": {
7	"model": "model",
8	"model_endpoint_type": "openai",
9	"context_window": 1,
10	"model_endpoint": "model_endpoint",
11	"model_wrapper": "model_wrapper",
12	"put_inner_thoughts_in_kwargs": true,
13	"handle": "handle",
14	"temperature": 1.1
15	},
16	"embedding_config": {
17	"embedding_endpoint_type": "openai",
18	"embedding_model": "embedding_model",
19	"embedding_dim": 1,
20	"embedding_endpoint": "embedding_endpoint",
21	"embedding_chunk_size": 1,
22	"handle": "handle",
23	"azure_endpoint": "azure_endpoint",
24	"azure_version": "azure_version",
25	"azure_deployment": "azure_deployment"
26	},
27	"memory": {
28	"blocks": [
29	{
30	"value": "value",
31	"id": "block-123e4567-e89b-12d3-a456-426614174000"
32	}
33	],
34	"prompt_template": "prompt_template"
35	},
36	"tools": [
37	{
38	"id": "tool-123e4567-e89b-12d3-a456-426614174000",
39	"tool_type": "custom",
40	"description": "description",
41	"source_type": "source_type",
42	"name": "name",
43	"tags": [
44	"tags"
45	],
46	"source_code": "source_code",
47	"json_schema": {
48	"key": "value"
49	},
50	"return_char_limit": 1,
51	"created_by_id": "created_by_id",
52	"last_updated_by_id": "last_updated_by_id"
53	}
54	],
55	"sources": [
56	{
57	"name": "name",
58	"embedding_config": {
59	"embedding_endpoint_type": "openai",
60	"embedding_model": "embedding_model",
61	"embedding_dim": 1
62	},
63	"id": "source-123e4567-e89b-12d3-a456-426614174000",
64	"description": "description",
65	"metadata": {
66	"key": "value"
67	},
68	"created_by_id": "created_by_id",
69	"last_updated_by_id": "last_updated_by_id",
70	"created_at": "2024-01-15T09:30:00Z",
71	"updated_at": "2024-01-15T09:30:00Z"
72	}
73	],
74	"tags": [
75	"tags"
76	],
77	"created_by_id": "created_by_id",
78	"last_updated_by_id": "last_updated_by_id",
79	"created_at": "2024-01-15T09:30:00Z",
80	"updated_at": "2024-01-15T09:30:00Z",
81	"tool_rules": [
82	{
83	"tool_name": "tool_name",
84	"type": "conditional",
85	"default_child": "default_child",
86	"child_output_mapping": {
87	"key": "value"
88	},
89	"require_output_mapping": true
90	}
91	],
92	"message_ids": [
93	"message_ids"
94	],
95	"description": "description",
96	"metadata": {
97	"key": "value"
98	},
99	"tool_exec_environment_variables": [
100	{
101	"key": "key",
102	"value": "value",
103	"agent_id": "agent_id",
104	"created_by_id": "created_by_id",
105	"last_updated_by_id": "last_updated_by_id",
106	"created_at": "2024-01-15T09:30:00Z",
107	"updated_at": "2024-01-15T09:30:00Z",
108	"id": "agent-env-123e4567-e89b-12d3-a456-426614174000",
109	"description": "description"
110	}
111	],
112	"project_id": "project_id",
113	"template_id": "template_id",
114	"base_template_id": "base_template_id"
115	}