Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Democratizing Reinforcement Learning for LLMs

Windows alt-tab on macOS

A small browser extension which shows a new tab page that Vimium can control

Android feed reader app

Flexible evaluation tool for language models

Enable SSH access to Kuberntes pods

Python bindings to the Zstandard (zstd) compression library

A feature-rich command-line audio/video downloader

Virtual whiteboard for sketching hand-drawn like diagrams

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

text window manager, shell multiplexer, integrated DevOps environment

CLI tool which enables you to login and retrieve AWS temporary credentials using a SAML IDP

Chrome extension to disable youtube video titles autotranslation

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

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

Web extension to set a default speed for video and audio

The official implementation of "Horizon Reduction Makes RL Scalable"

OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation

OCR Benchmark

日本の祝日を取得するライブラリ

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

MR.Q is a general-purpose model-free reinforcement learning algorithm.

Minimal reproduction of DeepSeek R1-Zero

Really Fast End-to-End Jax RL Implementations

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)