A straightforward method for training your LLM, from downloading data to generating text.
Scanning GitHub for open-source AI projects that are actually worth running: self-hostable, forkable, with a clear license. Star counts and languages are verified against each repository.
A straightforward method for training your LLM, from downloading data to generating text.
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
A one-click AI subtitle pipeline: cutting, translation, alignment and dubbing, aimed at Netflix-level quality for automated video localisation.
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
Faster Whisper transcription with CTranslate2
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
The open-source companion repository for Understanding AI Agents: Design Principles and Engineering Practice — full text, compiled PDF and per-chapter code.
The open-source AI voice studio. Clone, dictate, create.
Robust Speech Recognition via Large-Scale Weak Supervision
Easily train a good VC model with voice data <= 10 mins!
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Open-Sora: Democratizing Efficient Video Production for All
Wan: Open and Advanced Large-Scale Video Generative Models
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
AI-driven public opinion and trend monitor: aggregates hot topics across platforms plus RSS, filters by keyword, and pushes briefings to WeChat, Feishu, DingTalk and Telegram.
Hello-Agents: an open-source book and code repository that builds AI agents from scratch, principles first then implementation.
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.