An interface library for RL post training with environments.

SkyRL: A Modular Full-stack RL Library for LLMs

Scalable toolkit for efficient model reinforcement

Evaluate and improve models and agents using environments

Strongly typed APIs for non-empty collections, slices, iterators, and more.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Scientific computing that fits on a microcontroller. Estimation, control, kinematics, Lie groups, calculus, autodiff and linear algebra in stable no_std Rust with no heap, no panics and no unsafe. …

Rust integration for Unreal Engine 5

Legendary - A free and open-source replacement for the Epic Games Launcher

Programs to keep Docker login credentials safe by storing in platform keystores

AirSim is a simulator for drones, cars and more, built on Unreal Engine. We expand it with new implementations and sensor modalities.

Container images for running packaged Unreal Engine projects via the NVIDIA Container Toolkit

A framework built on top of NVIDIA Isaac Sim & PegasusSimulator for simulating fixed-wing UAVs

Agentic RL Training at Scale

Our library for RL environments + evals

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executa…

Deploy devcontainers onto any cloud provider, Kubernetes cluster, and docker.

Free monospaced font with programming ligatures

Script to add flashcards from text/markdown files to Anki

A Python 3 library for generating Anki decks

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

Orchard: An Open-Source Agentic Modeling Framework

Recent research papers about Foundation Models for Combinatorial Optimization

A communication bridge between the MOOS and ROS publish-and-subscribe middleware systems.

AirLLM 70B inference with single 4GB GPU

Library implementing type inference/checking functionality based on the Lean theorem prover