LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG
ComfyUI LLM Party is a custom node collection for ComfyUI that embeds LLM-driven agent workflows directly into the node-based image generation interface. It supports Claude and dozens of other models through OpenAI-compatible API endpoints, as well as local inference via Ollama, GGUF, and Hugging Face model IDs. The toolkit covers multi-tool calling, role-based agent configuration, word-vector RAG and GraphRAG for knowledge base management, radial and ring-style multi-agent pipelines, GOT-OCR2.0 for optical character recognition, GPT-SoVITS and ChatTTS for text-to-speech, and FLUX prompt generation nodes. Social platform connectors let workflows post to QQ, Feishu, and Discord directly. A notable detail is the built-in MCP server support, which allows these workflows to act as MCP-compatible tool providers. The project targets image generation artists who want LLM reasoning inside their existing ComfyUI pipelines, researchers tuning model parameters, and developers building production agents that combine language models with diffusion-based image generation.
- ✓Open-source license (AGPL-3.0)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
- ✓Documented (README)
git clone https://github.com/heshengtao/comfyui_LLM_party && cp comfyui_LLM_party/*.md ~/.claude/agents/Subagents overview
What people ask about comfyui_LLM_party
What is heshengtao/comfyui_LLM_party?
+
heshengtao/comfyui_LLM_party is subagents for the Claude AI ecosystem. LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG It has 2.3k GitHub stars and was last updated 3mo ago.
How do I install comfyui_LLM_party?
+
You can install comfyui_LLM_party by cloning the repository (https://github.com/heshengtao/comfyui_LLM_party) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is heshengtao/comfyui_LLM_party safe to use?
+
Our security agent has analyzed heshengtao/comfyui_LLM_party and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains heshengtao/comfyui_LLM_party?
+
heshengtao/comfyui_LLM_party is maintained by heshengtao. The last recorded GitHub activity is from 3mo ago, with 77 open issues.
Are there alternatives to comfyui_LLM_party?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy comfyui_LLM_party to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/heshengtao-comfyui-llm-party)<a href="https://claudewave.com/repo/heshengtao-comfyui-llm-party"><img src="https://claudewave.com/api/badge/heshengtao-comfyui-llm-party" alt="Featured on ClaudeWave: heshengtao/comfyui_LLM_party" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.