AI skills and agents for developers

Terminal-RSI-27B

Teriminal-RSI · Kit

Works through multi-step terminal tasks such as inspecting a repository, editing code and repairing dependencies. A 27.8B-parameter agent model built on Qwen3.…

gemma-4-12B

google · Kit

Google's Gemma 4 12B Unified model, an open model that reads text, images, audio and video and writes text, with a 256K context and no separate encoders. For d…

Hy4-preview

tencent · Kit

Generates text, code and documents with a Mixture-of-Experts model of 770B parameters that activates 49B and handles up to 1M context. For teams with the hardw…

WeVisOne-VL

Comfy-Org · Kit

Packs Tencent's WeVisOne-VL model files for ComfyUI, in 4B and 2B sizes with BF16 and int8 versions. For ComfyUI users who need the files in their text encoder…

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…

Recursive Flint

RecursiveSI · Kit

A 39.8B mixture-of-experts language model for coding agents that investigates codebases, fixes bugs, adds features and writes tests. For developers who run the…

Qwen3.8-27B-DSpine-b16-GGUF

aj9o9 · Kit

A GGUF draft model that speeds up Qwen3.8-27B in llama.cpp through speculative decoding, reaching about 125 tokens per second on code and math on one RTX 3090.…

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…

Qwenx86-4B (compact)

Quazim0t0 · Kit

Runs a calculator, Python and a C compiler inside its own weights, using 13 extra layers placed ahead of Qwen3.5-4B. For researchers and tinkerers who study mo…

embeddinggemma-2

google · Kit

Google DeepMind's open embedding model that places text, code, images, video and audio in one 768 number vector space, built to run on laptops and phones. Suit…

Generative_python_transformer

equ1 · Kit

A Gradio app from equ1 that, going by its name, generates Python code with a transformer model whose weights and tokenizer files sit in its repository. For dev…

Lama Example

CVPR · Kit

A Gradio app from the CVPR organisation with a large code base and sample images that point to filling in masked parts of a picture. Its README gives no descri…

GFPGAN Example

CVPR · Kit

A Gradio app from the CVPR organisation that carries the full GFPGAN face restoration code, built to try in a browser. Its README gives no description, so the…

Vela 3.0 · Studio

vllm-sr · Kit

Answers questions about an image or a text with a small 0.25B encoder running on CPU: point at an object, extract fields, catch OCR mistakes or decide between…

MuseTalkDemo

TMElyralab · Kit

A Docker-packaged demo app from TMElyralab for its MuseTalk model, bundled with DWPose, a Stable Diffusion autoencoder and ffmpeg tooling. It suits developers…

ProPainter

sczhou · Kit

Hosts the ProPainter project's code and its Gradio web demo, with scripts to run the model and to train it. Meant for people who want to try the demo or read h…

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…

Obfuscated-Shell Safety Leaderboard

FINAL-Bench · Kit

Ranks language models on whether they see through disguised shell commands, blocking the dangerous ones and allowing harmless encoded ones. A defensive safety…

Splat To Mesh

dylanebert · Kit

Packages a splat-to-mesh converter as a Docker app, by the name of its code, for turning gaussian splat scenes into 3D meshes. It suits 3D developers who want…

LGM-Mini

dylanebert · Kit

Runs a small Gradio demo built on the LGM model and several multi-view diffusion models, on a Hugging Face GPU. It suits people interested in 3D generation res…