Skip to content
Everruns

PATCH /v1/agents/{agent_id} - Update agent

PATCH
/v1/agents/{agent_id}

Parameters

Section titled “ Parameters ”

Path Parameters

Section titled “Path Parameters ”
agent_id
required
string

Agent ID (prefixed, e.g., agt_…)

Request Body required

Section titled “Request Body required ”

Request to update an agent. Only provided fields will be updated.

object
capabilities

Capabilities to enable for this agent with per-agent configuration. Replaces existing capabilities. Each has a ref (capability ID) and optional config.

array | null

Per-agent capability configuration

Associates a capability with an agent, including optional per-agent configuration. The config field allows the same capability to behave differently per-agent.

object
config

Per-agent configuration for this capability (capability-specific)

ref
required

Reference to the capability ID

string
Example
[
  {
    "config": {},
    "ref": "current_time"
  },
  {
    "config": {},
    "ref": "web_fetch"
  }
]
default_model_id

The ID of the default LLM model to use for this agent.

string | null
Example
model_01933b5a00007000800000000000001
description

A human-readable description of what the agent does.

string | null
Example
Updated description for the agent
name

The name of the agent. Used for display purposes.

string | null
Example
Updated Support Agent
status
One of:
null
system_prompt

The system prompt that defines the agent’s behavior and capabilities.

string | null
Example
You are an updated helpful assistant.
tags

Tags for organizing and filtering agents.

array | null
Example
[
  "updated-tag"
]

Responses

Section titled “ Responses ”

200

Section titled “200 ”

Agent updated successfully

Agent configuration for agentic loop. An agent defines the behavior and capabilities of an AI assistant.

object
capabilities

Capabilities enabled for this agent with per-agent configuration. Capabilities add tools and system prompt modifications.

Array<object>

Per-agent capability configuration

Associates a capability with an agent, including optional per-agent configuration. The config field allows the same capability to behave differently per-agent.

object
config

Per-agent configuration for this capability (capability-specific)

ref
required

Reference to the capability ID

string
created_at
required

Timestamp when the agent was created.

string format: date-time
default_model_id

Default LLM model ID for this agent. Can be overridden at the session level.

string | null
Example
model_01933b5a00007000800000000000001
description

Human-readable description of what the agent does.

string | null
id
required

External identifier (agent_<32-hex>). Shown as “id” in API. Client-supplied or auto-generated.

string
Example
agent_01933b5a000070008000000000000001
name
required

Display name of the agent.

string
status
required

Current lifecycle status of the agent.

string
Allowed values: active archived
system_prompt
required

System prompt that defines the agent’s behavior. Sent as the first message in every conversation.

string
tags

Tags for organizing and filtering agents.

Array<string>
updated_at
required

Timestamp when the agent was last updated.

string format: date-time
usage
One of:
null

400

Section titled “400 ”

Invalid agent ID or input exceeds allowed limits

Standard error response for API endpoints.

object
error
required

Error message describing what went wrong.

string

404

Section titled “404 ”

Agent not found

Standard error response for API endpoints.

object
error
required

Error message describing what went wrong.

string

500

Section titled “500 ”

Internal server error

Standard error response for API endpoints.

object
error
required

Error message describing what went wrong.

string