Launched this week
LiveReview
Free, Risk-Aware Code Review: Auto Approve Low-Risk Changes
430 followers
Free, Risk-Aware Code Review: Auto Approve Low-Risk Changes
430 followers
Most AI review tools flag issues. LiveReview promises production results: fewer incidents, fewer rollbacks, less senior reviewer load. Every PR is risk-scored. The lowest-risk 30-50% are safely auto-approved; the risky ones go straight to the engineers who should see them. The approach is inspired by Meta's highly successful internal AI review system, where production incidents fell 50x and rollbacks 3x. LLM + incident-trained ML + code-graph analysis. Free and self-hostable.
Free Options
Launch Team
ClarifyThe Full-Stack AI CRM that replaces 5 tools
Promoted
AI made writing code cheap, but PR reviews remain expensive. Seniors bottleneck every queue, skimming trivial and complex changes alike—letting risky code slip into production.
LiveReview solves this using the approach behind Meta's RADAR system: score change risk, fast-track safe code, and direct risky PRs to the right engineers.
Auto-Approve: Instantly passes low-risk PRs (30–50%); the rest always get human review.
Risk-First Review: Prioritizes high-risk PRs with comments sorted by blast radius.
Cognitive Coverage: Keeps your team informed via PR summaries, slides, or quizzes.
Livi Assistant: Natural-language insights on team metrics across web, Slack, Teams, and Discord.
Integrations & Models: Fits GitHub, GitLab, Bitbucket, Gitea, and Azure DevOps using LiveReview's model or your own API keys (15+ providers).
Free and self-hostable on your own infra.
Try it free: https://hexmos.com/livereview/
Star on GitHub: https://github.com/HexmosTech/LiveReview
@shrsv
noticed you feed production incidents back into the risk score unlike coderabbit.
btw how many merges or rollbacks does the ML need to process before that 30-50% auto approve rate actually becomes reliable for a new team?
@mohsinproduct That's highly org/codebase/deployment specific, but even a few days worth of data can will quickly capture "hotspots" and improve the classification significantly. There are also "high severity" but "rarely changed" things -- which do not become exposed this way. But for most orgs even 2 weeks good enough to capture the landscape I'd say.
@mogabr Hoping to make a contribution to the world of engineering -- including newcomers entering this field!
I'd definitely want to try this. We built our own review setup and are still improving it. I like that LiveReview promises production results, not more comments.
Two things I keep running into. With everyone on our team running 10+ coding agents in parallel, the rebase, re-review, rebase loop burns a lot of time and tokens. And it's hard to give the reviewer enough context to see the whole architecture, not just the diff. @shrsv how does LiveReview handle these?
@hungrydog Hi Ben, thanks for sharing about your review setup! Would love to learn more about it.
Token consumption: In LiveReview -- we have something called adaptive reviews, which gives you around 50% savings in terms of token cost using multiple models to get the job done
Architecture/Understanding: We have multiple cognitive coverage capabilities such as slides, issues filtering with detailed hierarchy, chatting with your entire dataset to improve practices, and also quizzes, etc. More can be done, but this is a start!
You can email me at shrijith <at> hexmos.com if you wish to have a more detailed discussion around this
congrats on the launch shrijith. auto approving low risk prs is where i would be careful. a tiny pricing or config change can look harmless in code but still affect customers. can those be marked as risky too?
@agshin_rajabov Thanks Agshin, for engaging!
Short answer: Yes, the size of the code is only one of the signals we use. We have blast radius analysis based on AST, production feedback, keywords, approval levels and such things to make it more intelligent.
On top of that -- the ML system can learn over time from production behaviors (incidents, rollback) to know which parts of code are tricky, etc as well.
The thing is -- over time -- the system level performance will improve -- lower downtime, reduced incidents, rollbacks, etc. So we aim for that.
By the way you can read Meta's RADAR paper on how this kind of system works in a real world case study: https://arxiv.org/abs/2605.30208
Interesting! So How does it work? Is it like a graphify kind of tool? that looks at blast radius and then does industry standard heuristic bench marks on what it finds etc? I assume no AI since its free and self hostable?
@alchemist_studio Hi Andre, thanks for engaging.
It combined around 20+ "signals" to create risk profile -- including things like graph based blast radius analysis, production performance feedback, code complexity, contributor trust levels, LLM semantic feedback, static analysis, etc. Essentially it's a custom risk scoring formula in a clean workflow.
It combines LLM, traditional ML, static checks -- pretty much any and everything that can contribute to risk profiling (aiming to be comprehensive and providing many levers to customize it exactly to the way an org needs it)
Free and self-hostable with my own Claude key is the part that would actually get me to try it — I don't love routing my code through another hosted reviewer. As a solo dev, the Cognitive Coverage bit is what caught my eye: walking a PR as slides before merging is a nice answer to the 'AI wrote it, I skimmed it' problem.
@jcbuilds We do have a docker image at our Github, you're welcome to try it out. Although we also have a cloud version for quickly understanding how it all works at a high level. And we support pretty much all major providers (you can mix and match) -- so that shouldn't be a problem as well.
Honestly, half the PRs I see barely need a review these days. This makes a lot of sense.
@shricodev1 Absolutely, the trick is in knowing which half is worth skipping :) And even within a PR which parts deserve attention is where we think can make a contribution to your workflow. Thanks for engaging!
Congrats on the launch!. Very interest. I am curious how the blast radius is calculated. Based on no of files any PR touches, no of line changes? does it also understand the blast radius based on business/functional impact?
@vishal_goswami7 The short answer is -- the blast radius calculated by indexing the repo into a tree structure, getting information of how all symbols are inter-related, and building up many signals on top of it and aggregating the result into a prioritization. (more here: https://hexmos.com/livereview/#risk-scoring)
Functional impact -- upto an extent yes, it can identify auth, payments, and other such critical areas; database access patterns, security and other things also get higher risk scores.
Business impact -- if you connect it to production data yes, since it can learn from your org context over time.