Letta Agents API
Create, list, modify, export, and delete stateful agents with memory and tools.
Letta Agents API is one of 41 APIs that Letta publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
This API exposes 14 JSON Schema definitions.
Tagged areas include Agents. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, pricing, a changelog, and 14 JSON Schemas.
This API exposes 56 operations across 49 paths, and defines 185 schemas. It is described by OpenAPI 3.2.0, at version 1.0.0.
Requests are made against 3 base URLs: https://api.letta.com, https://app.letta.com, http://localhost:8283.
56 operations
49 paths
185 schemas
2 DELETE18 GET20 PATCH16 POST
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 1
Letta Agents API declares
1 security scheme
for authenticating requests.
It accepts HTTP bearer tokens (bearerAuth).
By default, every request must be authenticated.
Paths & Operations 56
Across 49 paths, the API surfaces 56 operations — 2 DELETE, 18 GET, 20 PATCH, 16 POST. Each is listed below with its method, path, parameters, and response codes.
Agents 56
Create, list, modify, export, and delete stateful agents with memory and tools.
GET
/v1/agents/
List Agents
POST
/v1/agents/
Create Agent
GET
/v1/agents/count
Count Agents
GET
/v1/agents/{agent_id}/export
Export Agent
POST
/v1/agents/{agent_id}/export
Export Agent with Skills
POST
/v1/agents/import
Import Agent
GET
/v1/agents/{agent_id}/contextdeprecated
Retrieve Agent Context Window
PATCH
/v1/agents/{agent_id}
Modify Agent
GET
/v1/agents/{agent_id}
Retrieve Agent
DELETE
/v1/agents/{agent_id}
Delete Agent
GET
/v1/agents/{agent_id}/tools
List Tools for Agent
PATCH
/v1/agents/{agent_id}/tools/attach/{tool_id}
Attach Tool to Agent
PATCH
/v1/agents/{agent_id}/tools/detach/{tool_id}
Detach Tool from Agent
PATCH
/v1/agents/{agent_id}/tools/approval/{tool_name}
Modify Approval for Tool
POST
/v1/agents/{agent_id}/tools/{tool_name}/run
Run Tool for Agent
PATCH
/v1/agents/{agent_id}/sources/attach/{source_id}deprecated
Attach Source
PATCH
/v1/agents/{agent_id}/folders/attach/{folder_id}
Attach Folder to Agent
PATCH
/v1/agents/{agent_id}/sources/detach/{source_id}deprecated
Detach Source
PATCH
/v1/agents/{agent_id}/folders/detach/{folder_id}
Detach Folder from Agent
PATCH
/v1/agents/{agent_id}/files/close-all
Close All Files for Agent
PATCH
/v1/agents/{agent_id}/files/{file_id}/open
Open File for Agent
PATCH
/v1/agents/{agent_id}/files/{file_id}/close
Close File for Agent
GET
/v1/agents/{agent_id}/sourcesdeprecated
List Agent Sources
GET
/v1/agents/{agent_id}/folders
List Folders for Agent
GET
/v1/agents/{agent_id}/files
List Files for Agent
GET
/v1/agents/{agent_id}/core-memorydeprecated
Retrieve Agent Memory
GET
/v1/agents/{agent_id}/core-memory/blocks/{block_label}
Retrieve Block for Agent
PATCH
/v1/agents/{agent_id}/core-memory/blocks/{block_label}
Modify Block for Agent
GET
/v1/agents/{agent_id}/core-memory/blocks
List Blocks for Agent
POST
/v1/agents/{agent_id}/recompile
Recompile Agent
POST
/v1/agents/{agent_id}/system-prompt/recompiledeprecated
Recompile Agent System Prompt
PATCH
/v1/agents/{agent_id}/core-memory/blocks/attach/{block_id}
Attach Block to Agent
PATCH
/v1/agents/{agent_id}/core-memory/blocks/detach/{block_id}
Detach Block from Agent
PATCH
/v1/agents/{agent_id}/archives/attach/{archive_id}
Attach Archive to Agent
PATCH
/v1/agents/{agent_id}/archives/detach/{archive_id}
Detach Archive from Agent
PATCH
/v1/agents/{agent_id}/identities/attach/{identity_id}
Attach Identity to Agent
PATCH
/v1/agents/{agent_id}/identities/detach/{identity_id}
Detach Identity from Agent
GET
/v1/agents/{agent_id}/archival-memory
List Passages
POST
/v1/agents/{agent_id}/archival-memory
Create Passage
GET
/v1/agents/{agent_id}/archival-memory/search
Search Archival Memory
DELETE
/v1/agents/{agent_id}/archival-memory/{memory_id}
Delete Passage
GET
/v1/agents/{agent_id}/messages
List Messages
POST
/v1/agents/{agent_id}/messages
Send Message
PATCH
/v1/agents/{agent_id}/messages/{message_id}deprecated
Modify Message
POST
/v1/agents/{agent_id}/messages/streamdeprecated
Send Message Streaming
POST
/v1/agents/{agent_id}/messages/cancel
Cancel Message
POST
/v1/agents/{agent_id}/generate
Generate Completion
POST
/v1/agents/messages/search
Search Messages
POST
/v1/agents/{agent_id}/messages/async
Send Message Async
PATCH
/v1/agents/{agent_id}/reset-messages
Reset Messages
GET
/v1/agents/{agent_id}/groups
List Groups for Agent
POST
/v1/agents/{agent_id}/messages/preview-raw-payload
Preview Model Request
POST
/v1/agents/{agent_id}/summarize
Summarize Messages
POST
/v1/agents/search
Search Deployed Agents
GET
/v1/agents/search/count
Count Deployed Agents
GET
/v1/agents/{agent_id}/core-memory/variables
Retrieve Memory Variables
Schemas 185
The contract defines 185 schemas that model the data the API accepts and returns. The most detailed are letta__schemas__agent_file__AgentSchema (53 properties), CreateAgentRequest (48 properties), AgentState (45 properties), UpdateAgent (37 properties). Each schema is shown below with its type and property counts.
ToolReturnContent
object
4 properties
3 required
ZAIModelSettings
object
Z.ai (ZhipuAI) model configuration (OpenAI-compatible).
6 properties
OpenAIReasoning
object
1 property
SourceSchema
object
Source with human-readable ID for agent file
8 properties
2 required
TagSchema
object
1 property
1 required
UpdateAgent
object
37 properties
GoogleAIModelSettings
object
6 properties
OpenRouterModelSettings
object
OpenRouter model configuration (OpenAI-compatible).
5 properties
ImageContent
object
2 properties
1 required
SleeptimeManagerSchema
object
3 properties
1 required
Memory
object
Represents the in-context memory (i.e. Core memory) of the agent. This includes both the Block objects (labelled by sections), as well as tools to edit the blo…
5 properties
1 required
ToolCall
object
3 properties
3 required
ArchivalMemorySearchResponse
object
2 properties
2 required
ClientToolSchema
object
Schema for a client-side tool passed in the request. Client-side tools are executed by the client, not the server. When the agent calls a client-side tool, exe…
3 properties
1 required
ContextWindowOverview
object
Overview of the context window, including the number of messages and tokens.
23 properties
16 required
IdentityProperty
object
A property of an identity
3 properties
3 required
BasetenModelSettings
object
Baseten model configuration (OpenAI-compatible).
4 properties
ToolType
string
MCPServerSchema
object
MCP server schema for agent files with remapped ID.
6 properties
3 required
ManagerType
string
XAIModelSettings
object
xAI model configuration (OpenAI-compatible).
5 properties
Identity
object
8 properties
5 required
ToolJSONSchema
object
5 properties
3 required
NpmRequirement
object
2 properties
1 required
GenerateResponse
object
Response from direct LLM generation.
3 properties
3 required
RedactedReasoningContent
object
Sent via the Anthropic Messages API
2 properties
1 required
EmbeddingConfig
object
Configuration for embedding model connection and processing parameters.
10 properties
3 required
Group
object
18 properties
4 required
LettaMessageContentUnion
RoundRobinManager
object
2 properties
ToolExecutionResult
object
6 properties
1 required
ChatCompletionMessageFunctionToolCall-Output
object
A call to a function tool created by the model.
3 properties
3 required
MessageCreate
object
Request to create a message
8 properties
2 required
LettaAsyncRequest
object
17 properties
GeminiThinkingConfig
object
2 properties
CreateAgentRequest
object
CreateAgent model specifically for POST request body, excluding userid which comes from headers
48 properties
Block
object
A Block represents a reserved section of the LLM's context window.
19 properties
1 required
ClientSkillSchema
object
Schema for a client-side skill passed in the request. Client-side skills represent environment-provided capabilities (e.g. project-scoped skills) that are not…
3 properties
3 required
LettaStreamingRequest
object
20 properties
JsonObjectResponseFormat
object
Response format for JSON object responses.
1 property
ReasoningMessage
object
Representation of an agent's internal reasoning. Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Op…
13 properties
3 required
ToolReturnCreate
object
Submit tool return(s) from client-side tool execution. This is the preferred way to send tool results back to the agent after client-side tool execution. It is…
4 properties
1 required
ToolCallNode
object
Typed child override for prefilled arguments. When used in a ChildToolRule, if this child is selected next, its args will be applied as prefilled arguments (ov…
2 properties
1 required
AnthropicModelSettings
object
9 properties
MessageSearchResult
object
Result from a message search operation with scoring details.
5 properties
3 required
Message
object
Letta's internal representation of a message. Includes methods to convert to/from LLM provider formats. Attributes: id (str): The unique identifier of the mess…
25 properties
1 required
ToolReturnMessage
object
A message representing the return value of a tool call (generated by Letta executing the requested tool). Args: id (str): The ID of the message date (datetime)…
16 properties
5 required
AgentEnvironmentVariable
object
10 properties
3 required
SummarizedReasoningContent
object
The style of reasoning content returned by the OpenAI Responses API
4 properties
2 required
Passage
object
Representation of a passage, which is stored in archival memory.
15 properties
3 required
AgentFileSchema
object
Schema for serialized agent file that can be exported to JSON and imported into agent server.
10 properties
7 required
letta__schemas__openai__chat_completion_response__ChatCompletionTokenLogprob
object
4 properties
3 required
LettaUserMessageContentUnion
Source
object
(Deprecated: Use Folder) Representation of a source, which is a collection of files and passages.
11 properties
2 required
BedrockModelSettings
object
AWS Bedrock model configuration.
5 properties
CompactionStats
object
Statistics about a memory compaction operation.
6 properties
4 required
ReasoningContent
object
Sent via the Anthropic Messages API
4 properties
2 required
ParametersSchema
object
3 properties
1 required
ResetMessagesRequest
object
Request body for resetting messages on an agent.
1 property
ModifyApprovalRequest
object
Request body for modifying tool approval requirements.
1 property
1 required
ToolCallContent
object
5 properties
3 required
FileProcessingStatus
string
LettaStopReason
object
The stop reason from Letta indicating why agent loop stopped execution.
2 properties
1 required
GroqModelSettings
object
Groq model configuration (OpenAI-compatible).
5 properties
VectorDBProvider
string
Supported vector database providers for archival memory
CompactionResponse
object
3 properties
3 required
GroupSchema
object
Group with human-readable ID for agent file
7 properties
3 required
ApprovalCreate
object
Input to approve or deny a tool call request
7 properties
IdentityType
string
Enum to represent the type of the identity.
ChildToolRuleSchema
object
3 properties
3 required
ProviderCategory
string
letta__schemas__openai__chat_completion_response__ChoiceLogprobs
object
2 properties
InitToolRule
object
Represents the initial tool rule configuration.
4 properties
1 required
LettaToolReturnContentUnion
VoiceSleeptimeManagerSchema
object
4 properties
1 required
CompactionSettings-Output
object
Configuration for conversation compaction / summarization. Per-model settings (temperature, max tokens, etc.) are derived from the default configuration for th…
7 properties
OpenAIModelSettings
object
7 properties
ImportedAgentsResponse
object
Response model for imported agents
1 property
1 required
FunctionDefinition
object
4 properties
1 required
AzureModelSettings
object
Azure OpenAI model configuration (OpenAI-compatible).
5 properties
TurnTokenData
object
Token data for a single LLM generation turn in a multi-turn agent interaction. Used for RL training to track token IDs and logprobs across all LLM calls, not j…
5 properties
1 required
LettaErrorMessage
object
Error messages are used to notify the client of an error that occurred during the agent's execution.
6 properties
4 required
UserMessage
object
A message sent by the user. Never streamed back on a response, only used for cursor pagination. Args: id (str): The ID of the message date (datetime): The date…
11 properties
3 required
ValidationError
object
3 properties
3 required
SystemMessage
object
A message generated by the system. Never streamed back on a response, only used for cursor pagination. Args: id (str): The ID of the message date (datetime): T…
11 properties
3 required
UrlImage
object
2 properties
1 required
FileAgentSchema
object
File-Agent relationship with human-readable ID for agent file
10 properties
5 required
RequiredBeforeExitToolRule
object
Represents a tool rule configuration where this tool must be called before the agent loop can exit.
3 properties
1 required
BlockSchema
object
Block with human-readable ID for agent file
17 properties
3 required
ApprovalRequestMessage
object
A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution). Args: id (str): The ID of the message date (date…
12 properties
3 required
Body_export_agent
object
2 properties
Base64Image
object
4 properties
2 required
letta__schemas__letta_message__ToolReturn
object
6 properties
3 required
EventMessage
object
A message for notifying the developer that an event that has occured (e.g. a compaction). Events are NOT part of the context window.
12 properties
4 required
letta__schemas__agent_file__AgentSchema
object
Agent with human-readable ID for agent file
53 properties
1 required
HiddenReasoningMessage
object
Representation of an agent's internal reasoning where reasoning content has been hidden from the response. Args: id (str): The ID of the message date (datetime…
12 properties
3 required
TextResponseFormat
object
Response format for plain text responses.
1 property
TogetherModelSettings
object
Together AI model configuration (OpenAI-compatible).
5 properties
CompactionSettings-Input
object
Configuration for conversation compaction / summarization. Per-model settings (temperature, max tokens, etc.) are derived from the default configuration for th…
7 properties
MessageType
string
ToolCallMessage
object
A message representing a request to call a tool (generated by the LLM to trigger tool execution). Args: id (str): The ID of the message date (datetime): The da…
12 properties
3 required
SupervisorManagerSchema
object
2 properties
1 required
SummaryMessage
object
A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.
12 properties
3 required
MessageRole
string
LettaResponse
object
Response object from an agent interaction, consisting of the new messages generated by the agent and usage statistics. The type of the returned messages can be…
5 properties
3 required
MessageSearchRequest
object
Request model for searching messages across the organization
10 properties
AgentFileAttachment
object
Response model for agent file attachments showing file status in agent context
10 properties
6 required
SkillSchema
object
Skill schema for agent files. Skills are folders of instructions, scripts, and resources that agents can load. Either files (with SKILL.md) or sourceurl must b…
3 properties
1 required
BaseToolRuleSchema
object
2 properties
2 required
ContinueToolRule
object
Represents a tool rule configuration where if this tool gets called, it must continue the agent loop.
3 properties
1 required
RequiresApprovalToolRule
object
Represents a tool rule configuration which requires approval before the tool can be invoked.
3 properties
1 required
letta__serialize_schemas__pydantic_agent_schema__ToolSchema
object
12 properties
11 required
CoreMemoryBlockSchema
object
9 properties
8 required
ChatGPTOAuthReasoning
object
Reasoning configuration for ChatGPT OAuth models (GPT-5.x, o-series).
1 property
UpdateAssistantMessage
object
2 properties
1 required
TextContent
object
3 properties
1 required
LettaMessageUnion
PaginatedAgentFiles
object
Paginated response for agent files
3 properties
2 required
SummarizedReasoningContentPart
object
2 properties
2 required
Body_import_agent
object
13 properties
1 required
GoogleVertexModelSettings
object
6 properties
MaxCountPerStepToolRule
object
Represents a tool rule configuration which constrains the total number of times this tool can be invoked in a single step.
4 properties
2 required
CreateArchivalMemory
object
3 properties
1 required
letta__schemas__message__ToolReturn-Input
object
5 properties
1 required
ParentToolRule
object
A ToolRule that only allows a child tool to be called if the parent has been called.
4 properties
2 required
AgentState
object
Representation of an agent's state. This is the state of the agent at a given time, and is persisted in the DB backend. The state has all the information neede…
45 properties
10 required
GenerateRequest
object
Request for direct LLM generation without agent processing.
4 properties
1 required
UpdateUserMessage
object
2 properties
1 required
letta__schemas__message__ToolReturn-Output
object
5 properties
1 required
HTTPValidationError
object
1 property
letta__schemas__mcp_server__ToolExecuteRequest
object
Request to execute a tool.
1 property
IdentityPropertyType
string
Enum to represent the type of the identity property.
LettaRequest
object
16 properties
TerminalToolRule
object
Represents a terminal tool rule configuration where if this tool gets called, it must end the agent loop.
3 properties
1 required
FileSchema
object
File with human-readable ID for agent file
14 properties
2 required
ConditionalToolRuleSchema
object
5 properties
5 required
letta__schemas__agent_file__ToolSchema
object
Tool with human-readable ID for agent file
18 properties
1 required
ApprovalReturn
object
4 properties
2 required
ChatCompletionMessageFunctionToolCall-Input
object
A call to a function tool created by the model.
3 properties
3 required
AssistantMessage
object
A message sent by the LLM in response to user input. Used in the LLM context. Args: id (str): The ID of the message date (datetime): The date the message was c…
11 properties
3 required
AnthropicThinking
object
2 properties
openai__types__chat__chat_completion_message_function_tool_call__Function
object
The function that the model called.
2 properties
2 required
SGLangModelSettings
object
SGLang model configuration (OpenAI-compatible runtime with SGLang-specific parsing).
8 properties
letta__schemas__agent_file__MessageSchema
object
Message with human-readable ID for agent file
19 properties
3 required
LettaPing
object
A ping message used as a keepalive to prevent SSE streams from timing out during long running requests. Args: id (str): The ID of the message date (datetime):…
10 properties
2 required
JsonSchemaResponseFormat
object
Response format for JSON schema-based responses.
2 properties
1 required
LettaRequestConfig
object
4 properties
letta__serialize_schemas__pydantic_agent_schema__MessageSchema
object
10 properties
10 required
ExportAgentRequest
object
Request body for POST /export endpoint.
3 properties
CancelAgentRunRequest
object
1 property
BlockResponse
object
19 properties
2 required
Tool
object
Representation of a tool, which is a function that can be called by the agent.
18 properties
CreateBlock
object
Create a block
16 properties
2 required
ConditionalToolRule
object
A ToolRule that conditionally maps to different child tools based on the output.
6 properties
2 required
AgentType
string
Enum to represent the type of agent.
ToolEnvVarSchema
object
5 properties
5 required
FunctionTool
object
2 properties
2 required
ToolCallDelta
object
3 properties
PipRequirement
object
2 properties
1 required
FileBlock
object
23 properties
4 required
LettaStreamingResponse
Streaming response type for Server-Sent Events (SSE) endpoints. Each event in the stream will be one of these types.
UpdateReasoningMessage
object
2 properties
1 required
ArchivalMemorySearchResult
object
4 properties
3 required
letta__serialize_schemas__pydantic_agent_schema__AgentSchema
object
19 properties
18 required
ChildToolRule
object
A ToolRule represents a tool that can be invoked by the agent.
5 properties
2 required
ChatGPTOAuthModelSettings
object
ChatGPT OAuth model configuration (uses ChatGPT backend API).
5 properties
LettaAssistantMessageContentUnion
LettaImage
object
5 properties
1 required
letta__server__rest_api__routers__v1__agents__CompactionRequest
object
1 property
UpdateSystemMessage
object
2 properties
1 required
DeepseekModelSettings
object
Deepseek model configuration (OpenAI-compatible).
5 properties
ParameterProperties
object
2 properties
1 required
LLMConfig
object
Configuration for Language Model (LLM) connection and generation parameters. .. deprecated:: LLMConfig is deprecated and should not be used as an input or retu…
27 properties
3 required
letta__schemas__openai__chat_completion_response__TopLogprob
object
3 properties
2 required
LettaUsageStatistics
object
Usage statistics for the agent interaction. Attributes: completiontokens (int): The number of tokens generated by the agent. prompttokens (int): The number of…
10 properties
RunStatus
string
Status of the run.
ZAIThinking
object
Thinking configuration for ZAI GLM-4.5+ models.
2 properties
StopReasonType
string
BlockUpdate
object
Update a block
16 properties
Run
object
Representation of a run - a conversation or processing session for an agent. Runs track when agents process messages and maintain the relationship between agen…
17 properties
1 required
MaxCountPerStepToolRuleSchema
object
3 properties
3 required
OmittedReasoningContent
object
A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)
2 properties
ApprovalResponseMessage
object
A message representing a response form the user indicating whether a tool has been approved to run. Args: id (str): The ID of the message date (datetime): The…
14 properties
2 required
DynamicManagerSchema
object
4 properties
1 required
Function-Output
object
The function that the model called.
2 properties
2 required
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Letta 12
Other APIs Letta publishes across the network.
Letta Code
Letta Admin API
Letta Archives API
Letta Blocks API
Letta Client-Side Access Tokens API
Letta Conversations API
Letta Device Storage API
Letta Embeddings API
Letta Environments API
Letta Feeds API
Letta Folders API
Letta Groups API
#Agents
Where this information came from
This is an independent, third-party profile of Letta Agents API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.