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:
- fast snapshot / resume / fork for large parallel agent workflows
- infrastructure for agentic RL and environment versioning
- compatibility with projects like Shepherd, which models agent runs as Git-like reversible traces
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)→
More from coding & agent
- theo builds his own visualizer for today's agent models, showing how cheap Luna really is — ivan_bezdomny · 2026-09-23
- Vite+ Hits RC: One Rust-Powered CLI to Replace Your Entire Web Toolchain — cnakazawa · 2026-09-23
- Tesla's in-car Grok agent books trips across Gmail, Calendar and Notion in one command — xiaohu · 2026-09-23
- Tesla's In-Car Grok Assistant Now Executes Cross-App Tasks in One Sentence — xiaohu · 2026-09-23
- Garry Tan says Capy lets him ship PRs much faster than Codex or Claude Code — garrytan · 2026-09-23
- DeskPilot: open-source native Python desktop client for local LLMs with MCP and sandboxed tools — poofph · 2026-09-23