Machine Learning · GitHub

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

• A visual node graph for building and reusing image, video, audio, 3D, and text workflows without code.
• Reusable subgraphs, workflow templates, App Mode, and a local API for integrating workflows into applications.

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.

• Lyrics + style → score → full song - Source recording → melody score → a new interpretation - Musical feedback → score, style, or lyric revisions → a new recording
• Listen and inspect the score - Hear zero-shot covers - Follow an editing conversation

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

• 📊 87 composable skills — mix and match, or chain into full pipelines (/idea-discovery, /auto-review-loop, /paper-writing, /research-pipeline). See full catalog →
• 🔍 Literature & novelty — multi-source paper search (Zotero + Obsidian + local PDFs + arXiv/Scholar) + cross-model novelty verification

Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai

Dive into Deep Learning: for Chinese-language readers, runnable, and open to discussion. The Chinese and English editions are used for teaching at more than 500 universities in over 70 countries.

🤗 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.

• High performance on natural language understanding & generation, computer vision, audio, video, and multimodal tasks.
• Low barrier to entry for researchers, engineers, and developers.

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment.

12 Weeks, 24 Lessons, AI for All!

Inspect, visualize and intervene on any operation in any neural network. Capture every activation and gradient, the full computational graph and 800+ metadata fields without changing model code. Supports PyTorch, JAX, TensorFlow, MLX, PaddlePaddle and tinygrad. Validated on 6400+ models. Built for researchers and their AI agents.

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

Open Data Platform for analysts, quants and AI agents.

The fastest path to AI-powered full stack observability, even for lean teams.

• Real-Time - Per-second data collection and processing - Works in a beat – click and see results instantly
• Zero-Configuration - Automatic detection and discovery - Auto-discovers everything on the nodes it runs

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.