Event-driven network library for multi-threaded Linux server in C++11

A collection of formalized statements of conjectures in Lean.

DeepEP: an efficient expert-parallel communication library

Language model tokenization at GB/s

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Super basic implementation (gist-like) of RLMs with REPL environments.

LLM inference in C/C++

Xplane Demo for JSF C++ Standard

Thermodynamic Hypergraphical Model Library in JAX

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Agents' Last Exam

J-space / Jacobian-lens visualizer for Qwen3.6-27B (4-bit) on Apple Silicon, ported to Apple MLX

Companion code for the global workspace interpretability paper

JDK main-line development https://openjdk.org/projects/jdk

A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Feel free to report them yourself and take credit for the CVE if hand…

Command-line utility for monitoring GPU hardware.

A small, self-contained C implementation of Shamir's Secret Sharing (Adi Shamir, 1979) over GF(2^8)

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

An implementation of regular expressions for Rust. This implementation uses finite automata and guarantees linear time matching on all inputs.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

SAEs waste 74% of their features, cosine scoring finds the missing ones

The Art of Debugging Open Book

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.