[HN Gopher] Show HN: JavaFactory - IntelliJ plugin to generate J...
___________________________________________________________________
Show HN: JavaFactory - IntelliJ plugin to generate Java code
Hi HN, I built a code generator plugin for IntelliJ that uses LLMs
to create repetitive Java code like implementations, tests, and
fixtures -- based on custom natural-language patterns and
annotation-based references. Most tools like Copilot or Cursor aim
to be general, but fail to produce code that actually fits a
project structure or passes tests. So I made something more
explicit: define patterns + reference scope, and generate code
consistently. In this demo, 400 lines of Java were generated in 20
seconds -- and all tests passed:
https://www.youtube.com/watch?v=ReBCXKOpW3M GitHub:
https://github.com/JavaFactoryPluginDev/javafactory-plugin
Author : javafactory
Score : 37 points
Date : 2025-05-20 11:29 UTC (11 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| geodel wrote:
| Feels very Java like. Factories, repositories, utils, patterns
| etc. Good stuff.
| asdffdasy wrote:
| yoDawgMemesFactory
| cess11 wrote:
| The guide is a 404.
|
| "404 - page not found The
|
| master branch of
|
| javafactory-plugin does not contain the path
|
| docs/how-to-use.md."
|
| How do I hook it into local models? Does it support Ollama,
| Continue, that kind of thing? Do you collect telemetry?
| likis wrote:
| What LLM is it using? Is it something local? Or does it call out?
| It wasn't obvious from the docs, and I didn't want to dig through
| all of the code to figure it out. Should probably be clearly
| stated on the front page.
|
| But the project looks interesting, I have been looking for
| something similar.
| trollied wrote:
| It uses openai.
| simpaticoder wrote:
| If the trend continues a program will look like
| "JavaFactory("<prompt>").compile().run();".
| winrid wrote:
| I've always wondered how long until we reach this. If every pc
| can run models locally, with a given seed and prompt it could
| be the ultimate compression. It's also hilarious.
| imhoguy wrote:
| Although very lossy compression, each invocation will be
| different, so that will inevitably circle back to "strong-
| static-LLM" prompts. What? wait..!
| woodrowbarlow wrote:
| LLMs at their core do produce reproducible results with a
| given seed. it's all the workflow stuff people do on top
| that tends to break reproducibility.
| dibujaron wrote:
| This is not the case for LLMs running on GPUs (which is
| most of them); GPUs are non-deterministic for this use-
| case due to the floating point math involved. there is no
| way to get perfectly deterministic output from OpenAI
| despite the presence of seed and temperature parameters.
| AugustoCAS wrote:
| A side comment, I have found that configuring a few live
| templates in IntelliJ helps me to write a lot of the repetitive
| code just a handful of keystrokes regardless of the language.
|
| Structural refactoring is another amazing feature that is worth
| knowing.
| p0w3n3d wrote:
| As a programmer I feel bad if tests don't fail at the first
| run... It might show that they are not testing...
___________________________________________________________________
(page generated 2025-05-20 23:02 UTC)