Collection of LLM completions for reasoning-gym task datasets

maze datasets for investigating OOD behavior of ML systems

The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes

Assistive Gym, a physics-based simulation framework for physical human-robot interaction and robotic assistance.

Action for checking out a repo

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

Genome modeling and design across all domains of life

A pure MLX-based training pipeline for fine-tuning LLMs using GRPO on Apple Silicon.

An Extensible Deep Learning Library

POSIX compatibility layer for WASI builds

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

Create workflows that enable you to use Continuous Integration (CI) for your projects.

Xcode extension for GitHub Copilot

Flutter Sticky Headers - Lets you place "sticky headers" into any scrollable content in your Flutter app. No special wrappers or magic required. Maintainer: @slightfoot

Minimal hackable GRPO implementation

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

Scratch card widget which temporarily hides content from user.

RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with PostgreSQL or SQLite

JSON library for nelua

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Perforator is a cluster-wide continuous profiling tool designed for large data centers

Everything you need to build state-of-the-art foundation models, end-to-end.

Apptainer: Application containers for Linux