Effortlessly run LLM backends, APIs, frontends, and services with one command.

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

Interface for OuteTTS models.

Webscout is the all-in-one search and AI toolkit you need. Discover insights with Yep.com, DuckDuckGo, and Phind; access cutting-edge AI models; transcribe YouTube videos; generate temporary emails and phone numbers; perform text-to-speech conversions; and much more!

Joy Caption is a ComfyUI node using the LLaVA model to generate stylized image captions, supporting batch processing and GGUF models.

gguf node for comfyui

A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captioning and visual analysis.

Download models from the Ollama library, without Ollama

Gradio based tool to run opensource LLM models directly from Huggingface

Own your AI, search the web with it🌐😎

A Simple Viewer for EXIF and AI Metadata

Extract structured data from local or remote LLM models

gguf (GPT-Generated Unified Format) connector

Local character AI chatbot with chroma vector store memory and some scripts to process documents for Chroma

Some random tools for working with the GGUF file format

PyGPTPrompt: A CLI tool that manages context windows for AI models, facilitating user interaction and data ingestion for optimized long-term memory and task automation.

SwiftLet is a lightweight Python framework for running open-source Large Language Models (LLMs) locally using safetensors

GPU-accelerated LLaMA inference wrapper for legacy Vulkan-capable systems a Pythonic way to run AI with knowledge (Ilm) on fire (Vulkan).

A collection of cog models for use on Replicate

convert a saved pytorch model to gguf and generate as much corresponding ggml c code as possible