ComfyUI Runner for Openclaw

A streamlined utility for programmatically managing the lifecycle and health of local ComfyUI servers.

xtopher86
v1.0.0
Jan 26, 2026
2
5.9k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install comfyui-runner

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install comfyui-runner using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is ComfyUI Runner?

The ComfyUI Runner is a specialized tool within the ecosystem of Openclaw Skills designed to provide developers with granular control over their ComfyUI environments. It acts as a bridge between your orchestration layer and the local image generation server, allowing for automated management of server resources. By using this skill, users can ensure their generative AI backend is responsive and available without manual intervention.

This skill is particularly valuable for those building automated image generation pipelines where the server needs to be initialized or verified before processing starts. As part of the wider Openclaw Skills collection, it provides a consistent interface for status checks and process management, ensuring that your local AI stack remains stable and efficient.

ComfyUI Runner Use Cases

  • Automating the startup of image generation backends prior to executing automated design workflows.
  • Monitoring the health and connectivity of a ComfyUI instance to prevent failure in multi-step AI pipelines.
  • Implementing resource-saving measures by programmatically stopping server instances after large batch jobs are finalized using Openclaw Skills.
  • Managing remote ComfyUI instances via basic authentication and custom host configurations.

How ComfyUI Runner Works

  1. The skill loads configuration settings from environment variables or a local .env file to determine the target host and port.
  2. When the 'run' action is invoked, the skill attempts to execute the ComfyUI binary located in the system PATH or the local skill directory.
  3. The 'status' action triggers a curl command to the /health endpoint to verify if the server is reachable and active.
  4. If authentication is required, the skill includes basic auth headers in its communication with the ComfyUI server.
  5. The 'stop' command sends a termination signal to the managed process to ensure a clean shutdown of the server environment.

ComfyUI Runner Setup

To get started with ComfyUI Runner in your Openclaw Skills environment, ensure you have Node.js and curl installed. Configure your server details by setting environment variables:

export COMFYUI_HOST="127.0.0.1"
export COMFYUI_PORT="28188"
export COMFYUI_USER="admin"
export COMFYUI_PASS="password"

Alternatively, you can create a .env file in the skill directory containing these keys. Ensure the ComfyUI executable is accessible in your system's PATH.

ComfyUI Runner Data Schema & Taxonomy

The ComfyUI Runner uses a simple JSON schema for requests and relies on environment variables for configuration. Below is the metadata and configuration schema:

Variable Type Default Description
COMFYUI_HOST String 192.168.179.111 The IP or hostname of the target server.
COMFYUI_PORT Number 28188 The port the server is listening on.
COMFYUI_USER String Optional Username for basic authentication.
COMFYUI_PASS String Optional Password for basic authentication.

Request Format:

{
  "action": "run" | "stop" | "status"
}

ComfyUI Runner Advanced Features

  • Health check verification using the native ComfyUI /health endpoint for high reliability.
  • Basic authentication support for interacting with secured or remote server instances.
  • Flexible deployment options allowing the skill to run as part of a larger multi-agent system within Openclaw Skills.
  • Automatic process discovery if the binary is located in the local skill directory.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*