# heshengtao/comfyui_LLM_party

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

Repository: https://github.com/heshengtao/comfyui_LLM_party
Canonical: https://ross.abutalabs.com/products/comfyui_llm_party
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: comfyui, openai, workflow, agent, dify, graphrag, gemini, llama, ollama, omost, o1, gpt-sovits, linux, flux, gguf, vlm, ocr, mcp, janus-pro
Last push: 2026-07-29T18:05:53+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 28, longevity 62
- inputs: {"age_days": 872, "days_push": 35, "days_rel": 595, "gap_med": 52, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2343, forks 203 (observed 2026-08-28T04:06:39.031774+00:00)

## What it is
A ComfyUI plugin providing a comprehensive set of nodes for building LLM agent workflows, including MCP server support, RAG/GraphRAG, TTS, OCR, and integrations with chat platforms like Discord and Feishu. It adapts to virtually any LLM with OpenAI-compatible interfaces (o1, ollama, gemini, deepseek, qwen, etc.) as well as local models and GGUF files.

## Use cases
- build llm agent workflows in comfyui
- create an ai assistant with tool calling
- build a rag knowledge base over industry documents
- connect an llm chatbot to discord or feishu
- combine llm with tts and image generation for streaming
- run local llms like ollama or gguf models in a node graph
- build multi-agent interaction pipelines

## When to choose
- you already use ComfyUI and want to add LLM/agent capabilities to your image workflows
- you want a visual node-based way to orchestrate LLMs, RAG, TTS, and OCR together
- you need to plug an LLM assistant into Discord, Feishu, or QQ
- you want broad model compatibility including local GGUF and OpenAI-compatible APIs

## When to avoid
- you need a standalone agent framework without ComfyUI
- you want a code-first SDK rather than a node-graph UI
- your project requires a permissive license (AGPL-3.0)
- you only need simple chat without image/workflow integration

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, llm-inference, rag, mcp, chatbot, tts, speech-recognition, ocr, workflow-automation, prompt-engineering
- domain: large-language-models, chatbots, image-processing, developer-tools
- platform: python, windows, cross-platform
- tags: comfyui, llm-workflow, node-based, graphrag, gguf, ollama, openai-api, vlm, discord-bot, feishu, tts-integration, agent-workflows, ai-agents, retrieval-augmented-generation, linux, macos

## Member repositories
- heshengtao/comfyui_LLM_party (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:39.031774+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 2026-08-30T02:37:14.323386+00:00, confidence not recorded.
  - readme: https://github.com/heshengtao/comfyui_LLM_party (fetched 2026-08-28T04:06:39.031774+00:00, sha 7f7e29ba4b52)
- Data as of 2026-08-30T08:39:29.467469+00:00.