Wanted

One-click lightweight installer for Hermes Agent. Run your autonomous AI assistant locally on Windows, macOS with FTS5 memory, multi-platform gateway, and secure sandboxing.

日本語LLMまとめ - Overview of Japanese LLMs

Realtime demo, Streaming and Finetuning code for CSM

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

The HTML Presentation Framework

A pipeline parallel training script for diffusion models.

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

Suno AI Downloader

🎵 LyricWave – AI Music Composer (Proof of Concept) 🎶 A personal project exploring automatic generation of unique MP4 songs. LyricWave blends lyrics with AI-generated melodies and synthetic vocals to experiment with new forms of musical expression. A creative testbed to push your ideas into sound. 🚀🎧

A set of tools to download your music from Suno.ai with organized filenames and prompts.

ScriptFlow: Free, open-source AI-powered transcription tool. Transcribe any video / playlist or audio from files, YouTube, or 1000+ websites with a fast, lightweight, and private GUI application, and Many Export Formats.

Lets make video diffusion practical!

from pumpCurry

A python tool to explore and program SIMs / USIMs / ISIMs. Mirror of https://gitea.osmocom.org/sim-card/pysim

Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced single- and multi-image editing. Supports 7+ specialized LoRAs including photo-to-anime, multi-angle camera control, pose transfer (Any-Pose), upscaling, style transfer, light migration, and manga tone. Features fast inference (4 steps default).

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

This repo helps you understand how safetensors are structured to store different layers of an LLM and re-shard/re-chunk safetensors files even if they don't fit in the GPU.. ( No Autoclass )

Full version of wav2lip-onnx including face alignment and face enhancement and more...

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Python tool for converting files and office documents to Markdown.