Have been recently inspired by Open Interpreter, and I'm on a journey to build my own version from scratch!
Introducing Openmacro! Which aims to be a multiplatform personal agent which allows LLMs to run code locally. Openmacro aims to act as a personal agent capable of completing and automating simple to complex tasks autonomously via self prompting. The project is still in early development, and I just hit my second milestone that I'd love to share with you guys! I've made a scrapbook post about this a longggg time agoooo, but many improvements and changes have been made! Note this took a lot of arcade hours and it might have sessions seperated.
At the moment I've built the core base of the program, added a proper code interpreter, made an extensions engine and ecosystem, made a default browser extension for the web, custom config.toml
for custom personalities through cli, and so much more! And the best part, it leverages HuggingFace Spaces which means that you don't need any API key to get started.
You can access the GitHub repo here: github.com/Openmacro/openmacro
Or quickly get started by running
pip install openmacro
macro
Next steps:
Currently, focusing on a refined system for Extensions, so anyone can build extensions for openmacro.
- Working on browser
which is the official openmacro browser extension powered by Playwright, Bs4 and Markdownify.
- Working on ompi
which is the Openmacro Package Index. Similar to Python's pypi
, users can install third-party extensions to integrate with their openmacro assistant.