"🐈 nanobot: The Ultra-Lightweight OpenClaw"

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agent…

One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

A version of verl to support diverse tool use

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

An elegant PyTorch deep reinforcement learning library.

A bare-bones Python library for quality diversity optimization.

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Deep Neuroevolution

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

HKUST Thesis LaTeX3 Template (Available on Overleaf/TeXPage)

HKUST Thesis Typst Template

Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

LLM training in simple, raw C/CUDA, migrated into Rust

Examples and guides for using the OpenAI API

Harness LLMs with Multi-Agent Programming

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

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

Nano vLLM

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

An extension of the PyMARL codebase that includes additional algorithms and environment support

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

A testbed for multi-agent route planning.