Automate your AI music video workflow with Synesthesia Engine. This local Gradio app bridges audio analysis, LLM-driven storytelling, and LTX Desktop video generation. Simply drop in your song stem…

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

Let AI agents run research experiments + train small language models (in your browser!)

Gas Town - multi-agent workspace manager

Convert PDFs, EPUBs, DOCX, DOC, and TXT files into high-quality audiobooks using **Qwen3 TTS Voice Model** - an open-source voice synthesis system that excels at natural speech generation and voice…

ArtCraft is an intentional crafting engine for artists, designers, and filmmakers

A bot that can reproduce any image on demand on drawing applications like MS Paint and skribble.io

A general fine-tuning kit geared toward image/video/audio diffusion models.

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Run command in terminal with ComfyUI

AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs.

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

State-of-the-art TTS model under 25MB 😻

Run VSCode-based coding agents and extensions seamlessly within other IDE platforms - bridging the gap between VSCode ecosystem and other development environment.

Python package that numerically calculates the structure of probability distributions on statistical manifolds.

PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models

Advanced File content extractor for using on LLM

Zephyr is a declarative neural network library on top of JAX allowing for easy and fast neural network designing, creation, and manipulation

A JAX-based gravitational-wave population inference toolkit for parametric models

Profiling Google Gemma 3n Model Using PyTorch Profiler

Claude Code for Windows: No WSL. No Docker. Just code.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…

An open-source AI agent that brings the power of Gemini directly into your terminal.

A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.