19 August 2026

Open-source reinforcement learning framework Miles launches publicly

First reported

Latent Space and VentureBeat ran this on , all on the same day.

  • Miles, a reinforcement learning framework built over nine months by 72 contributors, became publicly available as open-source software.
  • The framework is designed to work with large language models and multimodal models, which process text, images, and other data types together.
  • Miles positions itself as infrastructure for building AI agents, systems that can take actions and learn from results.

How it was covered

Latent Spaceswyx & Alessio

Miles, an open-source RL framework developed over nine months with 72 contributors, launched as battle-tested infrastructure for LLMs and multimodal models. The newsletter presents it as a major OSS contribution to the agent harness ecosystem.

Reported by VentureBeat