PyTorch building blocks for the OLMo ecosystem

Optimized AI models for the edge

Enhance LLM problem-solving with REAP: Reflection, Explicit Problem Deconstruction, and Advanced Prompting. This repo includes the REAP prompt framework, code for reproducing experiments, datasets,…

Python package for compiling and analyzing quantum algorithms to simulate electronic structures.

A python package using machine learning to study symmetry.

Nano vLLM

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

🧠 Make your agents learn from experience. Based on the Agentic Context Engineering (ACE) framework.

OpenCUA: Open Foundations for Computer-Use Agents

go ATAK/CivTAK fast and simple server and client

The official firmware for Meshtastic, an open-source, off-grid mesh communication system.

Плагин для HA позволяющий использовать Ирину в качестве STT

llama.cpp-gfx906

Local development against a remote Kubernetes or OpenShift cluster

a graph explorer of the Epstein emails

Linux service for interacting with XR devices

Train your AI self, amplify you, bridge the world

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

RuQualBench: A benchmark for evaluating the quality of the Russian language in LLM responses

💻 A fully functional local AWS cloud stack. Develop and test your cloud & Serverless apps offline

Этот репозиторий содержит автоматически обновляемые правила маршрутизации V2Ray, основанные на данных о заблокированных доменах и адресах в России.

Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Tunnel, Mixed, HTTP)

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Build reliable Gen AI solutions without overhead 🍕

The best ChatGPT that $100 can buy.

Silero Stress — pre-trained enterprise-grade automated stress and homograph disambiguation for the Russian language

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.

Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.

Lightweight infinite reactive stream processing framework

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild