OpenDevin VS sgpt

Open Devin is an innovative open-source project that builds on the ideas and capabilities of Devin. Employing technologies like Docker and Kubernetes for secure code execution and featuring a user-friendly interface designed with React, Open Devin supports real-time developer interactions and adjustments. Its versatility is supported by a community-driven approach, encouraging developer contributions and rapid adaptation to new technologies.

We have an issue in OpenDevin to add Aider as an agent, if anyone wants to take a crack at it:

https://github.com/OpenDevin/OpenDevin/issues/120

So… don’t hold your breath. If you see someone building a UI (like this https://github.com/OpenDevin/OpenDevin/tree/main/frontend, https://github.com/stitionai/devika/tree/main/ui; just read the commit log, it’s basically just ui

Yes. If you link to the UI sections of a repo you will likely see "basically just ui" commit history.

I guess you could argue that it’s important “setup infrastructure” stuff that any project starts with… but I’m just sceptical.

Of course it's an early stage pilot, it's only been developed since the Devin hype, why should it compete in quality at this very early time?

Is this similar to Devin (https://github.com/OpenDevin/OpenDevin)?

> @justlin610: Me and @huybery are discussing about reproducing Devin. https://github.com/opendevin/opendevin Come and join us and see if we can make something great together!

Developers can thrive thanks to open source! I believe that AI's future lies in sharing and open-source principles. With tools such as Devin, developers have nothing to fear about job security. Rather, they gain a free personal programming assistant. This allows them to concentrate on generating innovative ideas, while the AI handles the technical tasks, ultimately freeing up their time.

I feel only a bit bad when deploying a billion dollar machine model to ask "how to rename a git a branch" every other week. Its the easiest way (https://github.com/tbckr/sgpt) compared to reading the manual, but reading the manual is the right way.

I've been saving a lot of time in the terminal recently with shell-gpt (https://github.com/tbckr/sgpt):

    $ sgpt -s "The command 'sp current' outputs

https://github.com/tbckr/sgpt

I totally agree with LLM+CLI are perfect fit.

One pattern I used recently was httrack + w3m dump + sgpt images with gpt vision to generate a 278K token specific knowledge base with a custom perl hack for a RAG that preserved the outline of the knowledge.

Which brings me to my question for you - have you seen anything unix philosophy aligned for processing inputs and doing RAG locally?