Learn the building blocks of how to build gpt-oss from scratch

A truly open version of gpt-oss which shows the entire pre-training from scratch

Open Source Application for Advanced LLM + Diffusion Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

MAESTRO is an AI-powered research application designed to streamline complex research tasks.

The official Python library for Arklex framework

DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses XTTS, OpenAI, ElevenLabs or Kokoro

Refine high-quality datasets and visual AI models

🍊 📊 💡 Orange: Interactive data analysis

Easy Jupyter development with Docker and Docker Compose

MongoDB, PostgreSQL and Express on Docker (docker-compose)

Exploring some cool datasets from AI conferences in 2024

Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Custom nodes for ComfyUI to generate empty latent space compatible with Hunyuan models for both image and video generation.

Summarize existing representative LLMs text datasets.

Run Stable Diffusion on Mac natively

👾 LM Studio TypeScript SDK (pre-release public alpha)

👾 LM Studio CLI

GPU-Jupyter: Leverage the flexibility of Jupyterlab through the power of your NVIDIA GPU to run your code from Tensorflow and Pytorch in collaborative notebooks on the GPU.

An iOS app that utilises Llama stack to preserve local culture and history

An app that brings language models directly to your phone.