Unified Schema-Based Information Extraction

Photo blog, reporting 🤓 EXIF camera details (aperture, shutter speed, ISO) for each image.

PyTorch building blocks for the OLMo ecosystem

Fast, accurate & comprehensive text measurement & layout

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.

AI agents running research on single-GPU nanochat training automatically

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Because `model.fit()` isn't an explanation

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

A platform for building proxies to bypass network restrictions.

Enforce the output format (JSON Schema, Regex etc) of a language model

Derivative-based regular expression engine for Rust

Static analysis for GitHub Actions

Edit Banana: A framework for converting statistical formats into editable.

FlashInfer: Kernel Library for LLM Serving

DFlash: Block Diffusion for Flash Speculative Decoding

🔍 🔎 For English Learners

Dream 7B, a large diffusion language model

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

A GUI to quickly manage your WSL2 instances

GIMBench is a benchmarking framework for evaluating Guided Infilling Models (GIM).

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

A python module to repair invalid JSON from LLMs

HaluMem is the first operation level hallucination evaluation benchmark tailored to agent memory systems.