Kits of AI agent skills, rules and prompts

Inpaint_Me

Huertas97 · Kit

Fills in or repairs chosen parts of an image with inpainting in a Streamlit page, with example images and results included. For photo editors and machine learn…

DeepSeek-V4.1-Flash-1017 Maya GGUF

peasantsmith · Kit

Runs a 748B DeepSeek mixture-of-experts model on a home PC through two GGUF quantizations made for Project Maya. For people with a big-RAM machine and a fast S…

AREX-2-i1-GGUF

mradermacher · Kit

Weighted GGUF quantizations of BAAI/AREX-2, a 26.9B vision model, in about two dozen sizes from 7.2 GB to 22.2 GB, plus an imatrix file for making your own qua…

flux_text_encoders

comfyanonymous · Kit

Supplies text encoder checkpoints for Flux image models, made for ComfyUI's DualClipLoader node. For ComfyUI users who run Flux on their own machine.

SeedVR2

Comfy-Org · Kit

Upscales images and video in ComfyUI with repackaged SeedVR2 3B and 7B files from ByteDance Seed, in several precision formats. For ComfyUI users who run upsca…

Raon-1 mini (GGUF)

KRAFTON · Kit

Runs a 28.8B mixture-of-experts model tuned for Korean chat, reasoning and tool-using agents in llama.cpp. GGUF copy of Raon-1 mini preview for people who run…

SmolLM3-3B

HuggingFaceTB · Kit

Writes text and answers questions as a small 3B open model with switchable step-by-step thinking, tool calling and long context, for developers who want a comp…

Fibo 2.0

Comfy-Org · Kit

Edits images in ComfyUI with repackaged Fibo 2.0 files from BRIA AI, in bf16 and int8 versions with Dev and Turbo edit workflows. For ComfyUI users working on…

gemma-4-E4B-it-GGUF

unsloth · Kit

A 4-bit GGUF copy of Google's Gemma 4 E4B instruction model, packaged by Unsloth for running on your own machine. It reads text and images and answers in text.

halogen-qwen3.8-flash-next

peonist-ai · Kit

Holds the model weights for halogen-flash-server, an engine that runs Qwen3.8-Flash-Next on AMD Strix Halo machines, for owners of that hardware who want the m…

Gemma4-12B v2 Coding + Agentic Edition

yuxinlu1 · Kit

A GGUF fine-tune of Google's Gemma 4 12B instruction model for coding and tool-using agent work, sized to run offline on a machine with about 4.5 GB of free me…

Qwopus3.8-27B-Coder-Flash-GGUF

Jackrong · Kit

Helps with coding and tool-using agent work as a GGUF fine-tune of Qwen3.8-27B, trained on about 200,000 code, agent and reasoning examples. For developers who…

Alpie Seed 9B GGUF

169Pi · Kit

Runs Alpie Seed 9B, an image-and-text model from 169Pi AI, on your own machine through GGUF files in three bit depths. Suits developers who want local vision-l…

Qwen2.5-Coder-7B-Instruct-GGUF

Qwen · Kit

Runs a 7B instruction-tuned coding model from Qwen on your own machine, packed as GGUF files in eight quantization levels. Made for developers who want code he…

Haas-ja-v1.0

third-intelligence · Kit

Turns Japanese speech into text with a 615.8M speech recognition model built for speed and accuracy. For developers and teams who transcribe Japanese audio on…

Muse Glimmer 30B

meta-models · Kit

Reads text and images and carries out agent tasks such as tool calls and multi-step reasoning on a local machine, in a 30B model distilled from Muse Spark. For…

Mach Boom

SyzygyResearch · Kit

Turns English text into speech on a single CPU core, using a 3.5-bit version of Gradium's Phonon 31m model that runs several times faster than real time, for d…

DeepSeek-V4.1-Flash-1017-GGUF

unsloth · Kit

Unsloth's GGUF quantizations of DeepSeek-V4.1-Flash-1017, a huge image-and-text model, for running locally on a machine with 128 GB or more of RAM. For people…

Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

A coding-focused GGUF build of Qwen3.8-Flash-Next with half its experts removed, cutting 354 GB at BF16 to 58.4 GB while keeping image input. For people with l…

DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF

ISTA-DASLab · Kit

An expert pruned and quantized GGUF of DeepSeek-V4.1-Flash-1017 from ISTA-DASLab, aimed at code and agent work, with transformer weights of 72.1 GB. Suits deve…

AREX-2

BAAI · Kit

Improves its own solutions over several rounds of propose, measure, reflect and revise, using a 27B model from BAAI. For agent researchers and developers worki…

paper-rec

bluebalam · Kit

A Gradio demo that recommends ten recent machine learning and AI papers from arXiv, based on titles, abstracts or keywords you give it. It suits researchers an…

Qwen 0.5B

Osstral · Kit

A small Gradio demo from Osstral that serves the Qwen2.5-0.5B-Instruct model, for people who want to try a tiny instruction-tuned model in a browser or on thei…

Local Model Explorer

LocalLLaMA · Kit

Shows which GGUF quantized models fit your graphics card, Mac or CPU, for people who run language models on their own machine and want to pick a file that work…

Finetune

josephwong135 · Kit

Packages Hugging Face's AutoTrain, a no-code way to train AI models, as a Docker app. For people who want to train a model without writing code, in a browser o…

RigidFormer

hugging-apps · Kit

Predicts how several rigid objects move and collide using a Transformer that works on point sets, and shows its rollouts next to simulator ground truth. For ph…

Clinassist Train

Gs2004 · Kit

Holds the training scripts and Gradio app used to tune a Qwen model for the author's Clinassist project with GRPO. Suits machine learning developers who want t…

FloraFind

crashn · Kit

Runs a Gradio app in the browser, backed by model training, evaluation and prediction code, with saved checkpoints and example files. It suits students and dev…

Axon Alzheimer Detection

BoTahex · Kit

Classifies the stage of Alzheimer's disease with a saved CNN model inside a Gradio demo. For people exploring machine learning on health data, not for medical…

SplitSafe - Audio ML Leakage Auditor

boobalanit · Kit

Checks the train, validation and test splits of an audio dataset for leaked copies and shared speakers, using audio fingerprints that need no GPU. For people w…

Portfolio Optimization (Python)

blackopsrepl · Kit

Shows a portfolio optimization problem from SolverForge as a Docker app that you open in a browser or build on your own machine. For people exploring solver de…

Streamlit Machine Translate

TiberiuCristianLeon · Kit

Translates text between languages in a browser page, with a choice of several open machine translation models. Suits anyone who needs a quick translation, or a…

Apertus Mini WebGPU

swiss-ai · Kit

Runs the Apertus Mini model on your own machine inside a web browser, using WebGPU, with no server to set up. It suits developers and curious users who want to…

Gpu Tflop Finder

muellerzr · Kit

Looks up the TFLOPs, a measure of compute speed, for a GPU in a small Gradio app. It suits machine learning engineers and hobbyists who compare cards or size a…

Midi Music Generator

skytnt · Kit

Composes MIDI music with AI music models, in the browser or on your own computer. For musicians, hobbyists and developers who want machine-made tunes in a form…

MLX Model Explorer

mlx-community · Kit

Helps Mac users find an MLX model and a quantization that suit their machine, in a static page that opens in any browser with nothing to install.

TabArena

TabArena · Kit

Ranks machine learning methods for tabular data with Elo ratings in a Gradio leaderboard, and serves the numbers to agents as JSON and MCP tools. For researche…

An n8n workflow that reads the last day of your inbox over IMAP, mutes promotions and asks a model in Ollama on your own machine which threads need action. Urg…

An n8n workflow that watches a folder on your own n8n machine. When a file arrives, a Mistral chat model picks a subfolder for each loose file, and a short she…

An n8n workflow that checks a text against a source document with Ollama models on your own machine. A fact-checking model marks each sentence Yes or No, and a…

An n8n workflow with a chat window. Each message goes through a Basic LLM Chain to a model served by Ollama on your own machine, and the answer comes back in t…

mujoco

google-deepmind · Kit

Simulates the physics of jointed bodies that touch their surroundings, fast and accurately, for work in robotics, biomechanics, animation and machine learning.…

nvke

dsx-ai-factory · Kit

Lets platform teams offer Kubernetes clusters to their customers, built on their own bare-metal NVIDIA GPU machines, with a separate control plane for each clu…

OpenMausBot

milind-soni · Kit

Gives you a team of AI bots in a desktop chat app, each one a Claude or Codex agent on your machine with its own cloud computer. Aimed at people who want an op…

Hugging Face Skills

huggingface · Skill

Hugging Face’s skills for AI and machine learning work on the Hub. One command line skill gets you started, and twenty-four more cover training, evaluation, da…

radar-cnpj-mcp

wendersoon · Kit

Lets an AI agent search Brazil's public CNPJ company registry by activity and region, using a local base built from the federal files. Free, with the data kept…

goose

aaif-goose · Kit

An open source AI agent that runs on your machine, as a desktop app, a CLI or an API. It works with many model providers and any MCP server. Setup notes cover…

exo

exo-explore · Kit

exo’s Apache-2.0 software that links your devices into one AI cluster, so a model too big for one machine can run across them. The setup notes cover the macOS…

OpenHands Agent Canvas

OpenHands · Kit

OpenHands’ open source, self-hosted control center for coding agents. One browser app runs the OpenHands agent, Claude Code, Codex, Gemini CLI, Pi or OpenCode…