Iconic font aggregator, collection, & patcher. 3,600+ icons, 50+ patched fonts: Hack, Source Code Pro, more. Glyph collections: Font Awesome, Material Design Icons, Octicons, & more

The agent that grows with you

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

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

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

Research on Coding Agents

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Slurm Exporter is a Prometheus exporter designed to scrape and expose a comprehensive range of performance and scheduling metrics from Slurm-managed clusters. It supports both CPU and GPU resource …

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

Slurm: A Highly Scalable Workload Manager

Export select slurm metrics to prometheus

A high-throughput and memory-efficient inference and serving engine for LLMs

Tools for building GPU clusters

[ACL 2025] Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis

Textbook on reinforcement learning from human feedback

A project to improve skills of large language models

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Fully open reproduction of DeepSeek-R1

Robust recipes to align language models with human and AI preferences

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

Ongoing research training transformer models at scale

High performance, multi-platform VNC client and server

An educational resource to help anyone learn deep reinforcement learning.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Training Sparse Autoencoders on Language Models

A library for mechanistic interpretability of GPT-style language models