Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Mooncake is a serving platform for Kimi, an LLM service from Moonshot AI, built around sharing and transferring the KV cache used during language-model inference. It supports disaggregated serving and data movement between inference, training, and rollout systems. The catalogue add-ons operate or integrate with Mooncake-based serving and transfer workflows.
Latest release v0.3.13.post1 · 31 Aug 2026
These files are kvcache-ai/Mooncake's own configuration. They tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 315 tok CLAUDE.md A 5 tok