Highlights
Stars
The Little Book of Reinforcement Learning
Frontier Models playing the board game Diplomacy.
Reconstructed source code for the Microprose game F-15 Strike Eagle 2 for MS-DOS
SocialJax: sequential social dilemma environments
Run a remote Dwarf Fortress instance and connect to it using your browser!
A unified robot learning framework powered by LuckyEngine
Python SDK for LuckyEngine robotics simulation
Post-training with Tinker
A JAX transport-economy learning environment for route planning, cargo flow, financing, and replayable agent benchmarks.
Gymnasium environment for multi-robot wire handling in MuJoCo
ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.
Terrain rendering algorithm in less than 20 lines of code
PPO (Proximal Policy Optimization) agent for training on Atari environments using C++ with libtorch, integrated with the Arcade Learning Environment (ALE) and built using Bazel.
The API to search, scrape, and interact with the web at scale. 🔥
Developer toolkit to migrate applications from the legacy OpenAI Completions/Chat Completions APIs to the unified Responses API, guided by Codex CLI
Chess analysis GUI for UCI engines, with extra features for Leela (Lc0) in particular.
The Moon's phases rendered in real-time in ASCII art
Local LLM Notepad is an offline plug-and-play app for running local large-language model. Drop the single bundled .exe onto a USB stick, walk up to any computer, and start chatting, brainstorming, …
A lightweight, powerful framework for multi-agent workflows and voice agents
Lightweight coding agent that runs in your terminal
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
Running any GGUF SLMs/LLMs locally, on-device in Android
Modular CSS Library that brings the beauty of Terminal UIs to the browser