Apps & Tools
Miles
Open RL framework for simple, efficient, and stable large-scale agentic training.
byRadixArk
PlayableOpen source
Miles media is blocked
Allow external media to connect to the provider and play this content.
Description
Miles is an open-source framework for large-scale model post-training, optimized for reinforcement learning and agentic workloads. It leverages SGLang for high-throughput rollouts and supports multi-turn, tool-using agents with native integrations for task sandboxes like E2B, Modal, and Daytona.
Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.