Hacker News new | ask | show | jobs
by cepstrum9 421 days ago
I’ve spent the last 2.5 months building a github app that runs LLM-powered code reviews — and I just launched it.

The tool is built specifically for solo developers. You install it on your repo, trigger a scan by creating a pull request, and it leaves structured review comments using OpenAI under the hood.

Funnily enough, I used the dev version of this app to review its own pull requests while building it. It helped me spot bugs, simplify structure, and keep quality high — all without needing another human in the loop.

I believe agentic tools will play a huge role in the future dev experience — and code review is just the first node. Long-term, I want this to evolve into a multi-layer agentic assistant that supports everything from brainstorming and design to CI/CD.

Feature roadmap: - Model integrations beyond OpenAI: Claude, Gemini, DeepSeek, LLaMA - Bring Your Own Model (BYOM) - Smarter review agents: repo memory, config-awareness, custom rules

Right now I’m focused on getting feedback from devs and evolving based on what actually helps.

Try it here: [https://codii.dev]

I’d love feedback on:

- Are the reviews useful or noisy?

- What would make this fit into your workflow?

- Anything obviously missing, confusing, or broken?

Happy to answer any questions! (feel free to dm me on X https://x.com/cepstrum9)