ai-agent

Mooncake

Name: Mooncake
Author: kvcache-ai

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

5,593 stars854 forksC++Updated 6/17/2026100% free · open source

About this skill

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Topics

disaggregation

inference

kvcache

llm

rdma

reinforcement-learning

sglang

tokenspeed

trt-llm

vllm

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

40.8M

repo size

Apache-2.0

license

Key files

.pre-commit-config.yaml

MAINTAINERS.md

README.md

requirements_docs.txt

requirements-dev.txt

File tree

.claude/

.claude-plugin/

.devcontainer/

.github/

benchmarks/

docker/

docs/

extern/

FAST25-release/

image/

monitoring/

mooncake-common/

mooncake-ep/

mooncake-integration/

mooncake-p2p-store/

mooncake-pg/

mooncake-rl/

mooncake-store/

mooncake-transfer-engine/

mooncake-wheel/

scripts/

.clang-format

.dockerignore

.gitignore

Quick Actions

Details

Creator

kvcache-ai

Language

C++

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 173,241

ollama: Run AI models

Get AI models up and running with ollama. For founders using Go and AI.

ai-agent★ 168,458

Improve Code with andrej-karpathy-skills

Get better code behavior with andrej-karpathy-skills, 165k+ GitHub stars, for founders using LLMs.

ai-agent★ 161,315

Transformers: AI Models

Get state-of-the-art machine learning models with Transformers, for startup founders, with 161k+ GitHub stars.

ai-agent★ 104,971

Gemini CLI

An open-source AI agent that brings the power of Gemini directly into your terminal.

ai-agent★ 82,875

RAGFlow: Smarter LLM Context

Get a superior context layer for LLMs with RAGFlow, a retrieval-augmented generation engine, ideal for founders in AI, with 82k+ GitHub stars.

ai-agent★ 82,793

Vllm

A high-throughput and memory-efficient inference and serving engine for LLMs