Stary staryxchen

Any drop in performance is strictly due to hitting the rate limit, not my (lack of) talent🤫

Achievements

kvcache-ai/Mooncake kvcache-ai/Mooncake Public

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

C++ 7k 1.5k
taco-project/FlexKV taco-project/FlexKV Public

Python 385 80
TencentCloud/CubeSandbox TencentCloud/CubeSandbox Public

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

Go 13.2k 1.2k
google-keep-mcp google-keep-mcp Public

A Model Context Protocol server that turns Google Keep into a note-free personal task and knowledge system for AI assistants.

Python 2
codebuddy-hud codebuddy-hud Public

A HUD-style status line for CodeBuddy Code

Python 1
NvLinkMonitor NvLinkMonitor Public

Real-time per-link NVLink bandwidth monitor + inter-GPU P2P benchmark for NVIDIA multi-GPU systems. Lightweight C++ — the monitor needs no CUDA toolkit.

C++ 2

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

There was an error while loading. Please reload this page.