vram-mcp
Level FSourceMCP server that lets AI agents share one NVIDIA GPU — cross-session model claims, real busy detection via NVML, protected eviction, and full VRAM visibility for Ollama + everything else holding memory
Installation
View source repo →Related servers
mainframe-mcp100% local knowledge and persistent memory for coding agents. GPU-accelerated hyn8nFair-code workflow automation platform with native AI capabilities. Combine visumarkitdown-mcpPython tool for converting files and office documents to Markdown.@oh-my-opencode/ast-grep-mcpOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of groh-my-openagentOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of gr@oh-my-opencode/git-bash-mcpOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of gr