git-lrc
Free, unlimited AI code reviews that run on commit
434 followers
Free, unlimited AI code reviews that run on commit
434 followers
GenAI is like a race car without brakes. It accelerates fast — you describe something, and large blocks of code appear instantly. But AI agents silently break things. They remove logic. Relax constraints. Introduce expensive cloud calls. Leak credentials. Change behavior without telling you. git-lrc is your braking system. It hooks into git commit and runs an AI review on every diff before it lands.
Free
Launch Team / Built With
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
Hi @shrsv currently i've installed model in my local machine. can git-lrc use the models that installed via local machine ?
@daycod Hi yes - you can use ollama models. You can type "lrc ui" and configure ollama model. We have support for all the popular models plus OpenRouter support also there.
@shrsv alright thank you for the explanation man. how about the OpenAI Compatible API ?
@daycod We do not support arbitrary endpoints with OpenAI compatibility. But probably something can be arranged by making any custom endpoint behind Ollama.
I really like the idea. But what exactly does it check? Are there internal rules or standards?
@mykyta_semenov_ Hi Mykyta,
It checks for issues that impact production stability, cost, and correctness of the system under scan.
Concretely, we have 40 subcategories, such as performance, security, correctness, implementation complexity, cloud cost, regressions, etc., which are automatically detected.
Do give it a try for yourself. Also, we already have some customization capabilities for teams and will be enhancing them further in the upcoming days.
Please email Shrijith at hexmos.com, and I will be happy to hear more about the exact kind of issues you want identified and adjust the software to meet your needs.
What if want to run code review on PR because most of time my time goes on reviewing PR so I don't commit code. In that case I pull branch locally do some testing and review code. how it will helpful in this case ?
This is exactly what I needed. I've been using Cursor and Claude Code heavily, and honestly the scariest part isn't the
AI writing bad code — it's me blindly accepting diffs without properly reviewing them. git-lrc sitting as a pre-commit hook forces me to actually look at what changed before it lands. The web UI with inline comments is a nice touch too,
feels like doing a PR review on my own code. Already set it up on two repos.
Congrats on the launch! I love the 'race car without brakes' analogy. Do you or will you support all kinds of linting standards?
@xinwei_xie Hi Vivian, thanks for launch.
Right now it is AI only, but I'm looking into integrating things like git leaks etc.
Do you have advice on your ideal interface for integrating linters and such things?
This looks like a very interesting and timely tool for SWEs. Now that AI-generated code is becoming the norm, having a way to quickly pinpoint failures and streamline reviews is a huge time-saver. Great job on solving a modern pain point!
@martin_cervantes Thank you, Martin, for the encouragement. Do give it a try if it's relevant to you. I'm happy to make adjustments to fit your workflow perfectly.
🚀🚀🚀