self-hosted plaform for secure execution of untrusted user or AI-generated code

Async RL Training at Scale

slime is an LLM post-training framework for RL Scaling.

A PyTorch native platform for training generative AI models

Grokking the Coding Interview: Patterns for Coding Questions Alternative

A microservice that allows you to add custom middleware to Pangolin / Traefik resources.

🙌 OpenHands: Code Less, Make More

A Next.js 15 template with Plate AI, plugins and components.

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

Etherpad: A modern really-real-time collaborative document editor.

A crate for making MCP (Model Context Protocol) compatible programs with rust

⚙️🦀 Build portable, modular & lightweight Fullstack Agents

Friends of OLMo and their links.

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Rust SDK for the Model Context Protocol (MCP)

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Optimizing inference proxy for LLMs

Tau LLM made with Unity 6 ML Agent

A reading list on LLM based Synthetic Data Generation 🔥

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

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

High-quality datasets, tools, and concepts for LLM fine-tuning.

A compact LLM pretrained in 9 days by using high quality data

Responsive and clean landing page built with Tailwind CSS and Flowbite