Starred repositories
Implement a reasoning LLM in PyTorch from scratch, step by step
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
MuScriptor is a multi-instrument music transcription model developed by Kyutai and Mirelo.
Companion code for the global workspace interpretability paper
Official implementation of AsymFlow, pi-Flow, GMFlow
A framework for efficient model inference with omni-modality models
Zonos2 is a leading open-weight text-to-speech MoE.
A straightforward method for training your LLM, from downloading data to generating text.
Miso TTS is an 8 billion, highly emotive text-to-speech model
High-Quality Voice Cloning TTS for 600+ Languages
Awesome Audio-Visual Intelligence, Survey of Audio-Visual Intelligence
MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
Open-source AI usage tracker — tokens, cost, and sessions across Claude Code, Codex, Hermes, Qoder, and more
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
CC GUI Client (VibeCoding Platform Designed for Developers)
An app to monitor the (Codex) situation
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.
Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Make Any Website into CLI & Use your logged-in browser by AI agent.
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.
YAML-native agent workflow execution engine, written in Rust