Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/everruns/everruns/llms.txt

Use this file to discover all available pages before exploring further.

​
POST /v1/agents

Create a new agent with the specified configuration. Agents define the system prompt, capabilities, and default model for agentic sessions.

​
Request Body

​
name
string
required
Agent name for display purposes. Maximum 2 KB.
​
system_prompt
string
required
Base system prompt for the agent. Capability prompts will be prepended to this. Maximum 1 MB.
​
description
string
Optional description of the agent’s purpose. Maximum 10 KB.
​
default_model_id
string
UUID of the default LLM model to use. Falls back to system default if not specified.
​
capabilities
array
List of capability references to enable. Maximum 250 items.Each capability can be:
  • Simple string reference: "current_time"
  • Object with config: { "ref": "web_fetch", "config": { "timeout_ms": 30000 } }
​
id
string
Optional client-supplied UUID. If provided, must be a valid UUID v4 or v7.

​
Response

Returns the created agent object.
​
id
string
UUID of the created agent
​
name
string
Agent name
​
system_prompt
string
Base system prompt
​
description
string
Optional description
​
default_model_id
string
UUID of default model
​
capabilities
array
Array of capability references
​
status
string
Agent status: active or archived
​
created_at
string
ISO 8601 timestamp of creation
​
updated_at
string
ISO 8601 timestamp of last update

​
Example Request

curl -X POST http://localhost:9300/v1/agents \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Research Assistant",
    "system_prompt": "You are a helpful research assistant with access to web search and file management.",
    "description": "General purpose research agent",
    "capabilities": [
      "current_time",
      "web_fetch",
      "session_file_system"
    ]
  }'

​
Example Response

{
  "id": "01933b5a-0000-7000-8000-000000000001",
  "name": "Research Assistant",
  "system_prompt": "You are a helpful research assistant with access to web search and file management.",
  "description": "General purpose research agent",
  "default_model_id": null,
  "capabilities": [
    "current_time",
    "web_fetch",
    "session_file_system"
  ],
  "status": "active",
  "created_at": "2024-01-15T10:30:00Z",
  "updated_at": "2024-01-15T10:30:00Z"
}

​
Input Validation

The API enforces size limits as protection against abuse:
  • Name: 2 KB maximum
  • Description: 10 KB maximum
  • System prompt: 1 MB maximum
  • Capabilities: 250 items maximum
Violations return 400 Bad Request with message “Input exceeds allowed limits”.

​
Error Responses

  • 400 Bad Request - Invalid input or size limits exceeded
  • 422 Unprocessable Entity - Validation error (invalid capability reference)
  • 500 Internal Server Error - Server error