Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telepho…

A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.

Web GUI for tmux optimized for AI agent TUIs, with support for iOS safari and mac w/ keyboard shortcuts

MoE training for Me and You and maybe other people

Neural Turing Machines (NTM) - PyTorch Implementation

This is a repo in-progress for Linear Semantic Control (LiSeCo)

Trio – a friendly Python library for async concurrency and I/O

Code and Data for Tau-Bench

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Hierarchical Reasoning Model Official Release

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model

OpenAlpha_Evolve is an open-source Python framework inspired by the groundbreaking research on autonomous coding agents like DeepMind's AlphaEvolve.

All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀

A Conversational Speech Generation Model

Discrete-time Signal Processing 3rd edition (Oppenheim)

Meta-learning local synaptic plasticity for continual familiarity detection

A syntax-highlighting pager for git, diff, grep, rg --json, and blame output

Base code for the Dingo quadruped; modified from Stanford Pupper and Notspot repositories. Includes integration with ROS Noetic and a simulation of the Dingo

Dotfiles for my Unix-flavoured systems. Includes configs for NeoVim (OVIWrite), Sketchybar, SKHD and yabai, as well KDE Plasma

My personal macOS configuration

Machine learning methods for DNA sequence analysis.

Official implementation of the paper 'Barzilai-Borwein-based Adaptive Learning Rate for Deep Learning' in PRL 2019