Currently in beta · Free to use

Your docs already have the rules.
Now they enforce themselves.

CodeReview AI reads your team's actual documentation — security policies, style guides, architecture standards — and checks every pull request against them. Findings cite the exact doc and line range. No guessing.

Install on GitHub See how it works

Your team's knowledge doesn't enforce itself.

The docs exist. The standards are written down. But none of it is wired into the review process where it actually matters.

🔄

Same comments, every PR

Senior engineers repeat the same feedback on every pull request. The naming convention, the auth pattern, the testing requirement. It's all in the docs, but nobody checks.

📋

New contributors fly blind

Onboarding docs, contributing guides, security policies — they exist in wikis and markdown files. New team members push code that violates standards nobody told them about.

Review bottlenecks slow shipping

When senior engineers are the only ones who know the rules, every PR waits in their queue. The obvious stuff should be flagged before a human opens the review.

How it works

Two minutes to set up. Zero config files.

Install the GitHub App. CodeReview scans your repo, finds your docs, classifies them into review gates, and starts reviewing PRs. That's it.

1

Install

One-click GitHub App install. Pick your repos. No tokens to manage, no webhooks to configure.

2

Scan

CodeReview scans your repo tree, finds documentation files, and classifies each into review gates: Security, Architecture, Style, Legal, Onboarding.

3

Confirm

You see what it found and confirm. Multi-topic docs get decomposed into gate-specific sections with exact line ranges. You're in control.

4

Review

Open a PR. CodeReview posts findings as a comment — traffic light summary, per-gate breakdown, doc citations. Done in seconds.

  Setup: scanning stripe/stripe-python
Connecting to GitHub for stripe/stripe-python... 0.4s
Scanning repository tree... 1.2s
Found 8 doc files in 4,217 repo files 1.3s
Classifying CONTRIBUTING.md (1/8) 2.1s
Classifying SECURITY.md (2/8) 2.8s
Decomposing README.md → 3 gate sections 3.6s
Classifying docs/ARCHITECTURE.md (4/8) 4.2s
Classifying docs/STYLE_GUIDE.md (5/8)...
  PR comment: pull request #142
🔴 CodeReview AI: RED
🔴 SECURITY
🔎 [HARDCODED_SECRET] API key hardcoded in config/settings.py on line 24. Secrets must be loaded from environment variables per your security policy. 📖 SECURITY.md, lines 18–22 📝 config/settings.py:24
🟡 STYLE
🔎 [NAMING] Function getData uses camelCase. Your style guide requires snake_case for Python. 📖 docs/STYLE_GUIDE.md, lines 31–35
🟢 ARCHITECTURE
✔ No issues found
🟢 LEGAL
✔ No issues found
🟢 ONBOARDING
✔ No issues found
Tested against: Cal.com Stripe Next.js Supabase

What makes it different

Every finding tells you where it came from.

Other tools check against generic rules. CodeReview AI checks against your team's actual documentation. And it tells you which is which.

🔎 DOCUMENT-BACKED

Finding came from your documentation. Cites the exact file, section, and line range. You can verify it in 10 seconds. This is a rule your team wrote down — the system is just enforcing it.

💭 AI SUGGESTION

Finding is the model's own suggestion based on general best practices. Clearly labeled so your team knows it's not from your docs. Useful context, but never presented as your policy.

Hallucination guard

A second AI pass re-reads every finding against the source document before posting. If it can't prove the finding from what's actually written, the finding gets killed. The system doesn't fabricate policy violations.

Living documentation

When a comment comes up that isn't in the docs yet — update the doc. CodeReview picks it up automatically before the next review. That comment never needs to be made again. The docs become a system, not shelf-ware.

We know we're asking for repo access.

We're a small team asking you to install a GitHub App on your private repos. We take that seriously. Here's how the system is built.

Fail-closed architecture

If the system can't prove a finding from your docs, the finding doesn't ship. If GitHub is unreachable, the review posts an error comment rather than failing silently. Every decision path has a fallback, and every fallback logs why.

Read-only by default

CodeReview AI reads your code diffs and documentation to produce review comments. It does not modify your code, merge PRs, or access anything outside the repositories you explicitly grant.

No code storage

Code diffs are processed in memory during the review and are not persisted. Your documentation is cached for review performance and refreshed on each scan. You can re-scan or disconnect at any time.

Full audit trail

Structured logging with request IDs runs through the entire pipeline. Every scan, classification, review, and verification step is traceable. You can see exactly what happened and why.

Pricing

Start free. Upgrade when it's earning its keep.

No credit card required. No contracts. Cancel anytime.

Free

$0
Your first 20 PR reviews
  • All 5 review gates
  • Document-backed findings
  • Hallucination guard
  • Traffic light summaries
  • Unlimited repos
Install free

We're early. We'd rather be honest about that.

CodeReview AI is in active beta. It works — it's been tested against production repos including Cal.com, Stripe, Next.js, and Supabase. But we're still learning from every install. If you're on a compliance-heavy team and willing to try it, we'd genuinely appreciate the feedback.

Try CodeReview AI →