Stars
A simple to deploy but feature rich S3 object storage server for your filesystem
Spanish legislation as a Git repo — every law is a Markdown file, every reform a commit. 8,600+ laws.
REFUGIO Madrid 2026: Un evento para combatir el derrotismo tecnológico en España y demostrar que you can simply do things. Charlas técnicas, un hackathon de IA para perfiles multidisciplinares, net…
Project N.O.M.A.D, is a self-contained, offline survival computer packed with critical tools, knowledge, and AI to keep you informed and empowered—anytime, anywhere.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
Setup guide for ML training on NVIDIA DGX Spark (GB10 Blackwell, CUDA 13, aarch64)
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Our library for RL environments + evals
Official repo for Learning to Reason for Long-Form Story Generation
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
Machine Learning Engineering Open Book
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Entropy Based Sampling and Parallel CoT Decoding
Puzzles for learning Triton
🤖 Crear Chatbot WhatsApp en minutos. Únete a este proyecto OpenSource
Fast BM25 search in Python, powered by Numpy and Numba
Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.
A PyTorch native platform for training generative AI models
PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval