ICLR 2026

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

Dyslexia-friendly output from any AI coding agent. One rules file for Claude Code, Cursor, Codex, Gemini CLI, Windsurf and more — full content kept, only the shape changes. Say 'dyslexia fit' to pe…

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Domain-agnostic multi-agent software design and evolution harness

Port of SPGL1 to python

The SOTA extractor pipeline

An ultra portable Keyboard Mouse Combo using the original Blackberry Q20 keyboard

The Latest, Smaller Tailscale for OpenWrt Devices. 适用于 OpenWrt 设备的 最新的、更小的 Tailscale。

Source code of "The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States" (arXiv: https://arxiv.org/abs/2412.17056)

Self-hosted audiobook and podcast server

[ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.

UI Plugin for KOReader by @elfbutt and @joshuacant

Display HA dashboards in kiosk mode directly on your HAOS server

Find dead Python code

Optimization benchmark for diffusion model training on dynamical systems

NanoGPT (124M) in 90 seconds

The full dataset behind paperswithcode.com

A Quirky Assortment of CuTe Kernels

A project to improve skills of large language models

Scalable toolkit for efficient model reinforcement

Ongoing research training transformer models at scale

Code for paper "Design Principles for Sparse Matrix Multiplication on the GPU" accepted to Euro-Par 2018

A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗

Robust recipes to align language models with human and AI preferences