-
Johns Hopkins University
- Baltimore, MD
- liby99.github.io
Starred repositories
Reverse engineering the mocopi trackers, with the eventual goal of streaming the data to SlimeVR
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Cranelift based backend for rustc
A modern Prolog implementation written mostly in Rust.
Autoware - the world's leading open-source software project for autonomous driving
A collection of formalized statements of conjectures in Lean.
Open-source implementation of AlphaEvolve
A compiler and scenario generator for the Scenic scenario description language.
A markup-based typesetting system that is powerful and easy to learn.
This is a public version of LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
A lightweight, powerful framework for multi-agent workflows
Open-source code analysis platform for C/C++/Java/Binary/Javascript/Python/Kotlin based on code property graphs. Discord https://discord.gg/vv4MH284Hc
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A ground-truth fuzzing benchmark suite based on real programs with real bugs.
A terminal workspace with batteries included
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
End-to-end Generative Optimization for AI Agents
XBOW Validation Benchmarks
Python utility to estimate, compare, and reweight RNA energetics across many secondary structure algorithms.
pytorch implementation for "RNA Secondary Structure Prediction By Learning Unrolled Algorithms"
The infrastructure behind the Scallop website.
Dafny is a verification-aware programming language
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.