LlamaPen
A browser-based, no-install graphical interface for chatting with Ollama and other local or OpenAI-compatible language model servers, with chats stored only in the browser.
LlamaPen is a web interface for local LLM providers such as Ollama, llama.cpp, LM Studio, Jan and vLLM, usable on desktop and mobile without installing anything beyond the model server itself. It renders Markdown, model "thinking" text and LaTeX math, supports custom tool calls, and offers a built-in model and download manager.
Chats are stored locally in the browser for privacy and near-instant load times, and requests only ever go to the providers the user configures, including any OpenAI-compatible endpoint added by hand. It works offline as a PWA, and can be run locally through Docker or through Bun, or accessed as a hosted site.