NeurIPS 2025: Improving Monte Carlo Tree Search for Symbolic Regression

A Python CLI tool that converts Claude Code transcript JSONL files into readable HTML / Markdown format.

Creepy device and browser fingerprinting

Open source collection of copy/paste components built with Polaris, Shopify's design system

♟️ Vectorized RL game environments in JAX

[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework

Cache PyTorch module outputs on-the-fly

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

Make great analog designs

This is the UPX compressed wader/static-ffmpeg (Dockerfile, CI image build)

Multi-arch docker image with ffmpeg/ffprobe binaries built as hardened static PIE binaries with no external dependencies

Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)

plasTeX plugin to build formalization blueprints.

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

3D Visualization of an GPT-style LLM

Python wrapper around sox.

python wrapper for rubberband

Open Source, Language Agnostic Mutation Testing

JTokkit is a Java tokenizer library designed for use with OpenAI models.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Video+code lecture on building nanoGPT from scratch

A python Linear Programming API

rtl88x2bu driver updated for current kernels.

This repository explains and provides examples for "concept anchoring" in GPT4.

Evaluator for the A::B Prompting Challenge

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A nearly-live implementation of OpenAI's Whisper.

Displays and filters bookmarks on search string, show parent folders. This is a Web Extension add-on version of the old "Bookmark search plus" XUL extension published by Alice0775, not working anym…

🔊 Text-prompted Generative Audio Model - With the ability to clone voices