Kits of AI agent skills, rules and prompts

Projected_gan

Stanford-CS236g · Kit

A Gradio demo built on a Projected GAN model trained on Pokemon pictures, published as an example by the Stanford-CS236g account. Suits students who want to se…

Uniformer_video_demo by Sense-X

Sense-X · Kit

A Gradio demo that runs the Sense-X UniFormer video model on a clip and reports its class, with three example videos included. Suits students and developers wh…

Uniformer_image_demo by Sense-X

Sense-X · Kit

A Gradio demo that runs the Sense-X UniFormer image model on a picture and reports its class, with a few example photos included. Suits students and developers…

Reconocimiento de emociones

Saturdays · Kit

A Gradio demo for emotion recognition on faces, with a face detection file and two saved emotion models in its repository. Suits students and developers who wa…

SharkTank_Analysis

Murtada · Kit

Opens a static page whose title points to an analysis of Shark Tank, made from one HTML file and one style sheet that you view in a browser. The listing does n…

Pheonix_Data_Dashboard

Masaaki · Kit

Opens a static dashboard page built from one HTML file and one style sheet, which you view in a browser. The listing does not say what data it shows, so it sui…

Supervised Contrastive Learning

keras-io · Kit

Lets you try a Keras model built for supervised contrastive learning in a Gradio page, in a browser or on your own computer. Aimed at students and developers w…

Danbooru Tags Transformer V2 with WD Tagger

John6666 · Kit

Labels an image with Danbooru-style tags and writes captions with Florence-2 models. Runs in the browser as a Gradio app, for people who label or caption anime…

free-claude-code

Alishahryar1 · Kit

Routes coding tools such as Claude Code, Codex and Aider to models from many providers, free and local ones included, from a terminal, IDE, phone or browser. A…

Qwen3.5-4B-3D-Html

mondk · Kit

A 4.2B text-generation model, fine-tuned from Qwen3.5-4B, that writes a 3D scene as one self-contained HTML file using Three.js. Open the file in a browser and…

Needle 2

Cactus-Compute · Kit

A 45M-parameter open model for tool calling, device use and structured extraction, packed into one 14 MB binary that runs in about 28 MB of RAM. For developers…

NorthCUA-Mini

beipo-ai · Kit

Reads screenshots and requests, then plans and issues actions to operate a desktop or browser. A 35B mixture-of-experts computer-use model with 3B active param…

Qwen3.5-0.8B Astra Weight Edit

JonathanColetti · Kit

Fixes the repeat loops that Qwen3.5-0.8B falls into in thinking mode by editing two weight tensors directly, with no training. A small image-text model for Tra…

OpenJev

openjev · Kit

Answers typed decisions about text, web pages and screenshots, picking a choice, a yes-or-no probability or a score from your own labels in one forward pass. F…

GTA world model

lucidml · Kit

Makes video from one start image while you hold keys, frame after frame, streamed to a browser. Weights and inference code for a world model trained on GTA5 ma…

NorthCUA-Pro

beipo-ai · Kit

Reads screenshots and requests, then writes reasoning and tool calls for an agent that drives a desktop or browser. For teams with a large GPU setup who build…

phonon-31m-en

gradium · Kit

A small English text-to-speech model that streams natural 24 kHz audio and runs on a laptop CPU, a phone or in a browser tab. For developers who want speech on…

Cactus runtime

Cactus-Compute · Kit

Provides prebuilt runtime binaries that run text, speech and vision models locally on phones, laptops, servers and browsers. For developers who ship on-device…

Romanian Speech Recognition

gigant · Kit

Turns Romanian speech into text in the browser with a wav2vec2 model, for anyone who has Romanian audio or wants a small Gradio speech demo to study.

ViTGPT2

gagan3012 · Kit

A Gradio app from gagan3012 that, going by its model names, describes a picture in words by pairing a ViT image encoder with a GPT-2 text decoder. For people w…