# ATH-MaaS/ComfyUI-Copilot

An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

Repository: https://github.com/ATH-MaaS/ComfyUI-Copilot
Canonical: https://ross.abutalabs.com/products/comfyui-copilot
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent, ai, comfy-ui, copilot, deepseek, deepseek-v3, gpt-4, llm-agent, rag, flux, stable-diffusion, comfyui, comfyui-nodes
Last push: 2026-04-07T04:23:08+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 76, release rhythm 31, longevity 40
- inputs: {"age_days": 565, "days_push": 148, "days_rel": 380, "gap_med": 89.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5489, forks 363 (observed 2026-08-28T04:09:19.789289+00:00)

## What it is
ComfyUI-Copilot is an AI-powered custom node for ComfyUI that acts as an intelligent assistant for building, debugging, and optimizing image-generation workflows. It uses LLM agents (with support for models like GPT-4 and DeepSeek) to generate workflows, detect and repair errors, and answer ComfyUI-related questions.

## Use cases
- generate ComfyUI workflows from natural language descriptions
- debug and fix errors in ComfyUI workflows automatically
- get recommendations for nodes and parameters in image generation pipelines
- answer questions about ComfyUI usage inside the interface
- tune parameters for Stable Diffusion and Flux workflows
- automate tedious workflow building in ComfyUI

## When to choose
- you use ComfyUI and want LLM assistance for building or debugging workflows
- you want one-click error detection and repair suggestions for image generation pipelines
- you prefer bringing your own API key for agent capabilities

## When to avoid
- you don't use ComfyUI or node-based image generation tools
- you rely on the built-in hosted API services, which have been suspended
- you need a fully offline assistant without any LLM API access

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, llm-inference, rag, chatbot, workflow-automation
- domain: artificial-intelligence, large-language-models, image-processing, developer-tools
- platform: python, cross-platform, self-hosted
- tags: comfyui, comfyui-nodes, stable-diffusion, flux, llm-agent, copilot, aigc, workflow-debugging, ai-agents

## Member repositories
- ATH-MaaS/ComfyUI-Copilot (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.789289+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:21.647211+00:00, confidence not recorded.
  - readme: https://github.com/ATH-MaaS/ComfyUI-Copilot (fetched 2026-08-28T04:09:19.789289+00:00, sha dfff042db267)
- Data as of 2026-08-30T08:39:29.467469+00:00.