A 1.5MB Local LLM Manager That Turns llama.cpp Into a Complete Desktop AI Workstation
Open Source | Ooor: A 1.5MB Local LLM Manager That Turns llama.cpp Into a Complete Desktop AI Workstation TL;DR : Ooor is a MIT-licensed, open-source Windows desktop app weighing just 1.5MB. It integrates llama.cpp engine management, a GGUF model library, a Hugging Face model marketplace, a resumable chunked downloader, a streaming chat console, and an Agent tool-calling layer. No Electron. No…
A 1.5MB open-source Windows desktop app called Ooor has been developed to manage llama.cpp engine and provide a complete desktop AI workstation. Unlike other LLM tools, Ooor is a pure local solution with no Electron, cloud services, telemetry, or accounts. It is a WinForms + .NET Framework 4.8 application that launches instantly and uses minimal RAM. Ooor integrates four roles: Llama Engine Manager, Model Library Manager, Downloader, Chat Console & Agent, and Agent Tool-calling Layer.
Features include a lightweight toolkit, privacy protection, one-click launch and OpenAI-compatible API, independent engine version management, local model library management with soft-delete capability, a built-in Hugging Face model marketplace, a real download manager with multi-chunk parallel downloads and resumable support, a streaming chat console with token sparkline and chunk timing visualization, and a tool-calling layer for fetching URLs and reading files.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
