Earlier this year, we built a small tool called git-lrc.

It fixed one problem: engineers committing AI-written code they had not read. git-lrc put a review in front of every commit, right in the terminal. In February, it reached #3 Product of the Day on Product Hunt, and it now has 1.5k+ GitHub stars.

As teams adopted it, a bigger problem showed up one step later, at the pull request.

AI made code cheap to write. Review stayed expensive.

Every PR waited in the same queue, for the same few senior engineers. A renamed variable and a rewritten payment flow got the same amount of attention.

Seniors became the bottleneck. They skimmed. Risky changes slipped through.

Today we are launching LiveReview: a risk-aware code review system built to fix exactly that.

Vote for LiveReview on Product Hunt →

What developers actually gain

1. Your safest 30–50% of PRs get approved automatically
Every pull request gets a risk score. The lowest-risk 30–50% are approved automatically. The rest go to the right human, in the right order, ranked by how much they actually matter. Choose a conservative, balanced, or aggressive policy.

2. A risk score trained on your own incidents
Every score is built from three signals:

  • Semantic LLM analysis: what the change actually does, in plain language.
  • A custom ML model: trained on your own production incidents, rollbacks, and overrides, not a generic dataset.
  • Static graph-based codebase analysis: how far the change reaches through your call graph, and what it touches.

3. Risk inside the diff, not just risk per PR
LiveReview scores every hunk inside the diff for blast radius. A 3-line change to a shared auth check can outrank a 300-line UI tweak. Your reviewer's attention goes to the riskiest code first, not spread evenly across the diff.

4. Checkpoints at every stage, not just the PR
Commit, before push, PR, CI/CD, and scheduled checks. You turn on only the stages that matter per repository. A throwaway repo is fine with commit-only checks. Payments, auth, and core infrastructure deserve the full harness.

5. CI/CD Gates: your rule, not a preset
Write the exact condition in jq, against the real findings from a review, and wire it into any pipeline as one HTTP call. A security-first team can block on any security finding at all. A fast-moving startup can block only on correctness and UX bugs.

6. You still understand the code AI writes
A fast review pipeline still leaves one risk: engineers approving code they never really understood. Cognitive Coverage gives you a 60-second summary deck for every review, and a PR quiz that takes under a minute.

7. Ask your engineering data a question
Livi answers in plain English, on the web or in Slack, Teams, and Discord, with over 50 chart types.

8. Works with your git provider and your AI key
GitHub, GitLab, Bitbucket, Gitea, and Azure DevOps. Reuse the Claude or OpenAI key you already pay for, or any of 15+ AI providers, or use the LiveReview model.

9. Free and self-hostable
Run it on your own infrastructure. No seats, no per-review bill that climbs as your team grows.

Why this matters now

Most AI code review tools add more comments to the pull request. More comments is not the goal. Fewer incidents, fewer rollbacks, and less senior reviewer time are the goal.

LiveReview follows the approach behind Meta's internal AI review system, RADAR: score every change for risk, fast-track the safe ones, and route the risky ones to the right reviewers. At Meta, this approach led to:

  • 50× fewer production incidents
  • 3× fewer rollbacks
  • 35% faster reviews

LiveReview brings the same idea to any team, on any git provider, self-hosted and free. The loop runs like this:

Track outcomes → Learn from the data → Automate selectively → Keep improving

The result: your reviewers stop reading every line of every diff, and start spending their full attention on the 50–70% of changes that actually carry risk.

LiveReview is built to be the layer that decides whether a human needs to look at all, and ranks what matters when they do.

On GitHub

LiveReview is source-available and hosted on GitHub. You can see how it works before trying it.

If you'd like more engineers to have this, star it on GitHub ⭐ to help devs discover LiveReview.

We are launching LiveReview on Product Hunt today. If this problem is familiar, an upvote and a comment is the single best way to help more engineering teams discover this approach.