Subscribe
Sign in
p/jacob-just-another-coding-botOpen Source AI Coding Agent for Real-World Tasks
Start new thread
Kevin Leneway

JACoB - Open Source AI Coding Agent for Real-World Tasks

by
JACoB (Just Another Coding Bot) is an open source AI-powered coding agent that extends your capabilities and boosts efficiency by completing mundane tasks, integrating with GitHub, Figma, and more, while maintaining existing workflows and coding standards.

Add a comment

Replies

Best
Kevin Leneway
Maker
📌
Hi Product Hunt! We're Kevin and Chris, the creators of JACoB (Just Another Coding Bot), an open-source AI coding agent designed to streamline the development process. As veteran developers, we know that while AI isn't perfect, it can be a valuable tool for tasks like code reviews, converting designs to React components, and writing high-quality GitHub issues. We’ve been building JACoB over the past year to assist with our real work, and today we’re open sourcing it under an Apache 2.0 license. Our goal is to create the first fully open-source tool that matches the quality and polish of many closed-source alternatives. JACoB focuses on specific, time-consuming tasks that AI handles well, like generating code from Figma designs, fixing simple bugs, and writing boilerplate code like API endpoints. You can even converse with JACoB to refine existing GitHub issues or help write new ones. It integrates seamlessly into your workflow, from GitHub issues to pull requests, ensuring all code passes tests before finalizing. JACoB is available on GitHub today, where you can customize it to your needs, such as running with local models. We're also developing a hosted version—sign up for the waitlist at jacb.ai. Currently, JACoB works best with JavaScript or TypeScript projects, especially with frameworks like Next.js. To evaluate JACoB’s real-world abilities, we created our own benchmark arena since none existed for design-to-code tools. JACoB outperformed eight popular tools and human-written code, scoring an ELO of 1183, over 100 points higher than the nearest competitor. More details on how we achieved this are available in the technical white paper found in the repo. AI is transforming software development, and we believe developers should lead this change, not large corporations. JACoB is our contribution to that future, respecting your privacy and security while remaining transparent and open. We'd love your feedback. Visit our GitHub repo to try it out and find more demo videos and a link to our technical white paper. We’re excited to hear your thoughts and answer any questions!
Ty Fiero
Congrats on the launch. Looking forward to trying it!
tela
I love this! The companies built today on automation-first principles and tools like JACoB are going to have such an advantage.
Aaron Altabet
Heck yeah! Stoked for the Figma capabilities.
Kevin Leneway
Maker
@aaron_altabet Thanks! I've tried a bunch of Figma plugins and everything is always in that "sort of works" bucket. The key to JACoB is that it's integrated with your actual codebase, so you get code that actually fits in with your coding style. There are often minor tweaks I need to make but it does save me a ton of time. Excited to finally share this and see what people think!
Peter Francis
Looking forward to giving this a spin!
Sambrit Adhikari
Love the figma integration. This is awesome, looking forwarding to using it!
Albert
congratulations kevin and chris on launching jacob. it's exciting to see open source tools that integrate ai into developer workflows. considering the integrations with github and figma, could you share how jacob handles different coding styles or conventions when generating code from designs?
Kevin Leneway
Maker
@mashy Sure, JACoB creates a source map of all of the files and functions in your repository, including the packages you have installed, custom styles/classes/components, etc.. We also have a command-line tool that creates a custom jacob.config file that can (optionally) be added to your repository that contains your preferences and styles. JACoB can then use that information to create custom prompts containing instructions for each of the unique attributes of your codebase. It really does make a big difference, as evidenced by our performance in the arena-style eval rankings we've used to evaluate JACoB's code output.