AI made code generation cheap. But it also made silent breakage cheap.
Large diffs. Subtle logic removals. Relaxed validations. Expensive cloud calls. Secrets slipping into logs. Most of this doesn’t get caught while generating code; it gets discovered in PR review, or worse, in production.
That’s exactly where git-lrc changes the game.
What developers actually gain
-
Review at the right moment. Every staged diff is reviewed before it gets committed. No extra dashboard. No context switching.
-
Faster understanding of AI-generated diffs. Inline AI comments highlight risky changes so you don’t have to manually scan hundreds of lines. You stay in control — AI assists, you decide.
-
Explicit engineering responsibility. Each commit is marked as: [reviewed] / [vouched] / [skipped]. The decision is written into your git log. Weeks later, your team can see which changes were reviewed and which were consciously shipped without review.
-
Unlimited and free. Bring your own free-tier Gemini API key. No seat-based pricing. No trial walls. No billing surprises.
Machine-wide setup in ~60 seconds. Install once. Hooks apply globally. Every repo on your machine is covered.
Why This Matters Now
AI scales code production. But quality doesn’t scale automatically.
git-lrc turns review into a habit:
Generate → Review → Fix → Iterate → Commit
That feedback loop reduces:
- security leaks
- performance regressions
- hidden logic removal
- “How did this get merged?” moments
It’s not another AI that writes code. It’s the brake system that keeps velocity safe.
On GitHub
git-lrc is source-available and hosted on
If you believe AI-assisted coding needs guardrails built for engineers, not dashboards built for sales, this tool will resonate.
Would really appreciate it if you could take a look. And if you like what we’re building, please drop a ⭐ on GitHub — that early support genuinely makes a difference.