Comfy-Cozy

Active·★ 15·MIT·Updated 2026-05-31

★ Hidden Gem★ Trending

Comfy Cozy is an AI agent that allows users to interact with ComfyUI using plain English, automating complex workflow tasks like loading, patching, and running generations. It learns user preferences over time, offers reversible changes, and supports multiple LLM providers.

Comfy-Cozy sits in the Workflow Automation category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Interact with ComfyUI using plain English to automate workflow tasks.. A representative use case is Loading and dynamically adjusting parameters of ComfyUI workflows.. The listed license is MIT. GitHub stars are currently 15. Relevant tags include ComfyUI Automation, LLM Agent.

#ComfyUI Automation#LLM Agent#Generative AI#Workflow Management#AI Assistant#Tool Use#Multimodal AI

Features

01Interact with ComfyUI using plain English to automate workflow tasks.

02All changes are non-destructive and reversible with a full undo stack.

03The agent learns and adapts to your personal style and preferences over multiple sessions.

04Supports multiple LLM providers (Anthropic, OpenAI, Gemini, Ollama) via a unified abstraction layer.

05Autonomous mode for self-composing and optimizing workflows based on creative intent.

Why choose it

+Interact with ComfyUI using plain English to automate workflow tasks.

+All changes are non-destructive and reversible with a full undo stack.

+Loading and dynamically adjusting parameters of ComfyUI workflows.

+Supports 9 platforms or runtime environments.

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.

Compatibility

Python

Runtime

Verified via docs

ComfyUI

Platform

Verified via docs

Anthropic

LLM Provider

Verified via docs

OpenAI

LLM Provider

Verified via docs

Google Gemini

LLM Provider

Verified via docs

Ollama

LLM Provider

Verified via docs

Quick start

$ git clone https://github.com/JosephOIbrahim/Comfy-Cozy.git

$ cd Comfy-Cozy

$ pip install -e .

Use cases

↳Loading and dynamically adjusting parameters of ComfyUI workflows.

↳Discovering, downloading, and wiring new models (e.g., from CivitAI, HuggingFace).

↳Automatically repairing broken workflows by installing missing nodes and fixing connections.

↳Analyzing generated outputs using Vision AI and suggesting improvements or optimizations.

↳Executing workflows with specified parameters and monitoring progress.

How it compares

≈Comfy-Cozy belongs to the Workflow Automation category and is best evaluated alongside similar tools instead of in isolation.

≈If your main requirement is closer to "Loading and dynamically adjusting parameters of ComfyUI workflows.", that use case is a better comparison lens than a flat feature checklist.

≈Comfy-Cozy's license, community traction, and deployment model all make more sense when compared in category context.

Alternatives

Gemini CLI★ 104.8k

An open-source AI agent that brings the power of Gemini directly into your terminal. Supports native MCP.

Features

Why choose it

Trade-offs

Compatibility

Quick start

Use cases

How it compares

Alternatives

Related searches

Comments

Features

Why choose it

Trade-offs

Compatibility

Quick start

Use cases

How it compares

Alternatives

Related searches

Comments