npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

@aijunior/dev

v0.3.21

Published

Your AI Contributor which codes itself

Downloads

59

Readme

Docs: Junior Documentation

Junior - AI-First IDE which fully writes its own code

Video: Junior codes itself

"Video: Junior codes itself"

Read-Code Environment

The future of coding is AI. Humans will rarely interact directly with the source code; instead, it will be generated by language models. This shift promises to significantly boost developer productivity and, hopefully, enhance the joy of programming. However, human oversight will remain necessary for the foreseeable future. We will supervise the work of the LLM, providing inputs such as business needs and strategic/architectural directions, and reviewing the generated code.

This introduces a completely new way of interacting with the codebase, and it also requires a rethinking of the user interface. 'Junior' is an attempt at addressing this.

Junior is not only AI-first but also mobile-first, although it still lacks some features to be truly usable on mobile.

Can LLMs Handle Large Codebases?

My original question was whether Large Language Models (LLMs) could manage extensive codebases. The key challenge is the model's context window, or its "Working Memory." This limitation means we couldn't fit an entire source code into the prompt, necessitating a way to selectively focus on relevant code segments for each editing task.

Surprisingly, the answer turned out to be yes. Early in its development, even without all essential features, Junior began self-coding. It started by generating a console prompt from a YAML file containing my English commands and a list of files and directories. I then manually transferred this into ChatGPT, saved the output as a shell script, and executed it. This process allowed Junior to edit and refine its own code, adding new features and performing refactorings. The moment it successfully modified its code was a revelation to me. Impressively, Junior entirely developed its web interface, including both backend and frontend.

Getting Started

npm install -g @aijunior/dev
mkdir junior-tryout
cd junior-tryout
junior

Note: Junior is an experimental project at this time, not production ready.

For more info read the docs at https://aijunior.dev

Contributing and Support

Your contributions make a difference! At Junior, we value the collaboration of the community. Your role as a contributor is to monitor the development, provide detailed prompts, and thoroughly review the generated outcomes.

For support, please create an issue in the GitHub repository.

Similar tools

There are more mature tools for helping developers utilize language models. The most notable one is aider at https://aider.chat