comfyui_LLM_party
LLM workflow framework based on ComfyUI, supporting multiple LLM interfaces and tools.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 2.3k
- Source
- mcp-github
- Repository
- github.com/heshengtao/comfyui_LLM_party
Overview
comfyui_LLM_party is an LLM agent framework built on ComfyUI, including MCP server, Omost, GPT-sovits, ChatTTS, GOT-OCR2.0, and FLUX prompt nodes. It supports integration with Feishu, Discord, and all LLMs with OpenAI/AISuite-like interfaces, such as o1, ollama, gemini, etc. Additionally, it supports local LLMs, VLMs, and gguf format models. The framework enables users to quickly and easily build their own LLM workflows and seamlessly integrate them into existing image workflows.
Capabilities
- ▪Multiple LLM tool calling
- ▪Role setting
- ▪Industry-specific vector RAG
- ▪Complex agent interaction patterns
- ▪Social app integration
- ▪TTS integration
Use cases
Setup
Refer to the quick start guide on the project homepage to download the Windows portable package or use your existing ComfyUI installation to add missing nodes.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started?
Please refer to the quick start guide on the project homepage.
What LLM interfaces are supported?
Supports OpenAI/AISuite interfaces and local models.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
recon-skills
Security testing toolkit covering vulnerability detection for CORS, XSS, SQLi, and more.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.