Moonshot open-sources AgentENV for large-scale agent environments and RL

shi_weiyan · x · 2026-07-28

Moonshot says it has open-sourced AgentENV with kvcache-ai: a distributed system for running agent environments at scale.

The project powers agentic RL training for Kimi K3 and is designed around:

The post also highlights a potential combo: Shepherd’s reversible traces plus AgentENV’s environment management for meta-agents that supervise, optimize, and train other agents.

Related event: Moonshot Open-Sources AgentENV for Large-Scale Agent Training(2 posts)→

Original post →

More from coding & agent

coding & agent channel →