AI skills and agents for developers

Gender-Classifier-Mini

prithivMLmods · Kit

Sorts a photo into two classes, female or male, with a fine-tuned SigLIP 2 image model. Made for developers and researchers who want a small Python classifier…

MOSS-Video-Preview-Real-Time-SFT

OpenMOSS-Team · Kit

Comments on video while it plays, taking frames one by one and answering with low delay. For developers and researchers building live video assistants in Pytho…

Florence-2-large

microsoft · Kit

Captions images, finds objects and reads text in pictures when you pair an image with a short task prompt. Made for developers and researchers who run vision t…

Maincoder-1B

Maincode · Kit

Completes and writes Python code from a function signature or a docstring. A 1B code model from Maincode that is small enough to run on consumer hardware, for…

LightVAE

lightx2v · Kit

Swaps in lighter video autoencoder parts for Wan2.1, Wan2.2 and MiniMax-H3, through a ComfyUI node or a Python script. For video AI users who want compact VAE…

InstantID by InstantX

InstantX · Kit

Generates new images of a person from one face photo and a text prompt, keeping the face recognizable. Made for developers and artists who run Stable Diffusion…

OCR Tamil

GnanaPrasath · Kit

Reads Tamil and English text from photos of signboards, nameplates and storefronts, and the author says it copes with tilted text better than document-focused…

theOG-50M

DrunkkToys · Kit

Writes a Python function from a plain English request. A 50M parameter code model trained from scratch on one laptop, small enough to run offline in Ollama, LM…

Ming 3.0 TTS 0.5B GGUF

audio-cpp · Kit

GGUF packages of Ming 3.0 TTS 0.5B for the audio.cpp runtime: speech from text, voice cloning and voice design in seven languages, with mono 44.1 kHz output an…

faster-whisper-small

Systran · Kit

Whisper small converted to the CTranslate2 format so faster-whisper can transcribe audio with it. For developers who want local speech-to-text in Python.

Pocket TTS

kyutai · Kit

A 100M-parameter text-to-speech model from Kyutai that runs on CPUs in six languages, streams audio with about 200 ms to the first chunk, and works from Python…

Qwopus3.8-27B-Flash-V2-GGUF

Jackrong · Kit

Trims wasted reasoning in long agent tasks, as a GGUF build of the second Flash fine-tune of Qwen3.8-27B with better Python formatting. For people who run agen…

Spark-X2.6-4B-Blender

hotocooo · Kit

Writes Blender 5.x Python scripts that build clean, quad-dominant meshes such as props, furniture, products and human or animal base meshes. A 4B fine-tune of…

bekko-static-v1-slim-100k

flowercomputers · Kit

Turns text into 1024-dimension vectors with a static embedding model, trimmed to 25 languages. Fast sentence similarity and retrieval, without a transformer, i…

UltraGliClass v0.1

Srimon12 · Kit

A 154M-parameter zero-shot text classifier that scores every label you pass in one pass, for single-label, multi-label and intent tasks, including long inputs.…

Kokoro-82M-v1.0-ONNX

onnx-community · Kit

Turns English text into spoken audio with Kokoro, an 82 million parameter text-to-speech model packaged as ONNX files for JavaScript and Python. For developers…

SmolLM2-135M-Instruct

HuggingFaceTB · Kit

Answers chat-style questions and handles rewriting and summaries with a 135M-parameter instruction-tuned model small enough for on-device use. For developers w…

Needle 3

Cactus-Compute · Kit

A small on-device model from Cactus Compute for tool calling, structured extraction and text embeddings, used through the cactus Python package. For developers…

Whistle

Cactus-Compute · Kit

Transcribes speech in seven languages with word timestamps and speech embeddings, in a model only 16.9 MB in size. Runs from a short Python script, for develop…

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…

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…

CnOCR Demo

breezedeus · Kit

A Gradio demo of CnOCR, a Python OCR toolkit that reads English, numbers, Chinese and vertical text from pictures. It suits people who want to try it before in…

Gradio Demo

Abdoulayegk · Kit

A small Gradio app you can try in the browser or run on your own computer with Python. Its README gives no description, so you learn what it does by opening it.

Deepfake Detection System

saimuddineni · Kit

A Gradio app named for deepfake detection, for checking whether media may be fake. Runs in your browser on Hugging Face or on your own computer with Python 3.1…

TRELLIS.2-Text-to-3D (Rerun)

prithivMLmods · Kit

Turn a text prompt or a picture into a 3D model with Microsoft's TRELLIS.2 in a Gradio app. Runs in your browser or on your own computer with Python 3.12.

Idol Imagine Fast

prithivMLmods · Kit

Make images from text prompts in a Gradio app built on the idol, Z-Image-Turbo and BiRefNet models. Runs in your browser or on your own computer with Python 3.…

Lms Pab Backend

Oyabb · Kit

A Python app packaged with Docker that listens on port 7860 and is named as a backend. The notes do not describe its job, so this page covers its files and how…

MiniCPM5 2B Demo

openbmb · Kit

A Gradio demo from openbmb where you try the MiniCPM5-2B language model in a browser, or run a copy of the app yourself with Python 3.12.

Example for IS445

jnaiman · Kit

Runs a small Streamlit app labelled as an example for IS445, either online in a browser or from a local copy with Python. The page itself does not say what the…

Basal-1.5 Demo & API

jglowa · Kit

A Gradio demo and API for the basal-1.5 models by Remek Kinas, in three variants named 4.5B, max and mini, online or on your computer with Python 3.12.

Ultimate RVC

JackismyShephard · Kit

A Gradio app from the Ultimate RVC project for voice conversion, source separation, feature extraction and training, which runs online or on your computer with…

Video Background Removal

innova-ai · Kit

Removes or swaps the background of a video using the BiRefNet models, and runs online in the browser or on your own computer with Python.

Bark by ibyteohdear

ibyteohdear · Kit

A small Gradio demo from ibyteohdear for the suno/bark model, which runs online in the browser or on your own computer with Python.

StdGEN

hyz317 · Kit

A Gradio app from hyz317 whose repository holds staged inference scripts and a Blender folder, which runs online in the browser or on your own computer with Py…

Zeroscope V2

hysts · Kit

A Gradio demo from hysts for text-to-video generation with the zeroscope_v2_576w model, which runs online in the browser or on your computer with Python 3.12.1…

SmolVLM

HuggingFaceTB · Kit

A Gradio demo from HuggingFaceTB for the SmolVLM2-2.2B-Instruct model, with example images included, that runs online in the browser or on your computer with P…

Repo duplicator

huggingface-projects · Kit

A small Gradio app from huggingface-projects, named for duplicating repositories, that runs online in the browser or on your own computer with Python.

Bowdet

Haotian-Yuan · Kit

A Python web app from Haotian-Yuan packaged with Docker, served on port 7860 and open to try in the browser. Its page does not say what it detects, so check th…

Sand3D Assets Explorer

fffiloni · Kit

Browses Sand3D objects in 3D, moves their joints and shows the Python program behind each one. For people who work with these simulation-style 3D assets and wa…

Airshare Backend

AshikPlays19 · Kit

Runs a Python app built with Gradio that its name marks as the back end of an Airshare project. The README gives no description, so what it serves is not state…

TinyCodeAgent

Agents-MCP-Hackathon · Kit

An agent that solves tasks by writing Python, running it and fixing its own errors, built on TinyAgent with a Qwen model. Also works as an MCP server. For agen…

Qwen3 VL Demo

Qwen · Kit

A Gradio demo from the Qwen team for its Qwen3 VL vision-language family. Runs in your browser, or on your own computer with Python.

LBM Relighting

jasperai · Kit

A Gradio app from jasperai for fast image relighting with Latent Bridge Matching, which runs online in the browser or on your computer with Python 3.12.

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.…

ClickHouse Agent Skills

ClickHouse · Skill

ClickHouse’s official skills for coding agents. They review table designs and queries against written rules, advise on architecture, troubleshoot Node.js clien…

ruff

astral-sh · Kit

Checks Python code for mistakes and style problems and reformats it, written in Rust for speed. For Python developers who want a linter and a formatter in one…

Scrapling

D4Vinci · Kit

This Python web scraping framework combines fast HTTP requests, browser automation, and data parsing into one library. It includes an MCP server for AI agents…

ChatDev

OpenBMB · Kit

OpenBMB’s open-source platform for building multi-agent systems without code, in version 2.0 also called DevAll. You draw or write a workflow of LLM agents, th…

AutoGen

microsoft · Kit

Microsoft’s framework for multi-agent AI apps in Python and .NET, with the AgentChat API and AutoGen Studio, a no-code GUI. Its README now calls the project ar…

Agno

agno-agi · Kit

Agno’s open-source platform for building agents and running them as services. Your coding agent sets up a template with AgentOS, an API, an MCP server and Post…

Protocol Buffers

protocolbuffers · Kit

Google’s open source way to describe structured data in a .proto file and read and write it from many languages. The setup notes cover the protoc compiler and…

Crawl4AI

unclecode · Kit

UncleCode’s open source web crawler and scraper for language models and AI agents. It loads a page in a browser and returns clean Markdown, or JSON in a shape…

Claude Cookbooks

anthropics · Kit

Anthropic’s notebooks and Python examples for building with the Claude API. Folders cover tool use, retrieval, Skills, Claude Agent SDK and Managed Agents. The…

Supervision

roboflow · Kit

Roboflow’s free, open source Python library for computer vision applications. It draws detections, counts objects in zones, converts datasets and scores models…

MarkItDown

microsoft · Kit

Microsoft’s free, open source Python tool that converts PDF, Word, Excel, PowerPoint and other files to Markdown for LLMs. The setup notes cover the command li…

Awesome LLM Apps

Shubhamsaboo · Kit

Shubham Saboo’s open source collection of AI agents, agent skills and RAG apps, most in a folder of their own with a README. Setup notes cover the skills for C…

text-to-cad

earthtojake · Skill

earthtojake’s plugin that gives Claude Code, Codex, Cursor, Gemini and Grok local workflows for CAD. Your agent writes each model as a Python script and builds…