Data over sound, measured: 36.6 kbps laptop↔phone acoustic modem — portable C library, adaptive OFDM + graceful degradation to a never-zero floor, whitepaper + full measurement record

A collection of TLA⁺ specifications of varying complexities.

Self-directed Jupyter notebooks for engineers evaluating LangSmith during a POC. The modules cover the full agent engineering loop — build, trace, evaluate, deploy, and surface failure modes — agai…

Language model tokenization at GB/s

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

Fast TraceRoute: massively parallel CLI & Rust library for network observation

Leetcode for Pytorch

Python 3.14, compiled to metal — JIT & AoT native compiler and runtime in Rust. Cranelift backend, ruff parser, Green Tea GC, byte-exact differential testing against CPython.

Open implementation of Attention Residuals (Kimi Team, arXiv:2603.15031)

Official implementation of Learning The Pareto Front With HyperNetworks [ICLR 2021]

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

The batteries-included agent harness.

Inspect: A framework for large language model evaluations

slime is an LLM post-training framework for RL Scaling.

Spec-driven development (SDD) for AI coding assistants.

Google Cloud Knowledge Catalog Tools and Samples

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.

nv-one-logger enables tracking of GPU application progress over time and can help to identify overhead from workload and cluster inefficiencies to provide efficiency metrics.

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Liquid Audio - Speech-to-Speech audio models by Liquid AI

TokenSpeed is a speed-of-light LLM inference engine.

This is a local docker container that ingrates into langchain llm just like langsmith. Provides traces for llm and LangGrah

Architecture, patterns & internals of Anthropic's AI coding agent — reverse-engineered from source maps

A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems