RAMP, or Resource-Aware Model Proxy, is an open-source local LLM daemon that calibrates model size to available RAM, VRAM, and disk space. It provides a proxy layer for local inference workflows using tools such as llama.cpp and Ollama, with an OpenAI-compatible API.
RAMP is an Other infrastructure project. It focuses on running local language models reliably across machines with different RAM, VRAM, and disk capacity. RAMP is an open-source project aimed at developers and local AI enthusiasts. The project is open source (MIT). RAMP is available on the command line and API, and it can be self-hosted.
It is developed by Shivapreetham, and it first shipped in 2026. Development happens publicly on GitHub with 8 commits in the last 90 days. Key capabilities include resource calibration, model sizing, and RAM detection. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do