Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

Show HN: AnythingLLM Fork as NPM Package

A developer has created an NPM package fork of AnythingLLM, aiming for a lighter-weight, easier-to-install version with modified agent mode code focused more on automation.

Background

- AnythingLLM is an open-source desktop application that lets you run local AI models (like Llama, Mistral, GPT-4, etc.) for document chat, RAG (retrieval-augmented generation), and custom AI agents — essentially a ChatGPT-like interface you can run on your own machine with your own files. - This fork, Totem-LLM, repackages AnythingLLM as an NPM package (which means developers can install it with a single command via Node.js's package manager) and strips it down to be lighter and easier to integrate into other projects. The author has been rewriting the "agent mode" — the part of the app that allows AI to perform multi-step tasks autonomously — to focus more on automation rather than interactive chat. - Why it matters: AnythingLLM is popular among developers who want privacy (no data sent to cloud) and control over model choice, but the full desktop app is heavy and not designed for headless or programmatic use. This fork addresses that gap, aiming to offer a more developer-friendly, automation-first version of the same core functionality.

Related stories