close

Local and CI code review

The code review workflow you control

Multi-agent review that runs before you commit and on every pull request, on whatever model you choose. You own the workflow, the model, and the cost.

Start free

10 reviews a month. No credit card.

Works with Claude Code today.

AI writes more of your code every month

What it ships carries real risks.

A review step is no longer optional. The question is where it runs and what it costs.

One workflow, two places it runs

Revue is the same review engine in the two places that matter.

Two ways to use Revue

Start locally, before you commit. Add CI when your team wants every pull request reviewed automatically.

Primary

Claude Code skill

Stage your changes and type /revue in Claude Code. Six agents review in parallel (security, performance, code quality, architecture, synthesis, and verification) before your code lands in a commit. Fix what they flag, commit clean.

Get started free

CI pipeline

When a pull request opens, Revue triggers automatically in your pipeline. The same six agents review the diff and post findings as inline comments on the PR, before your team begins the human review. Works on GitHub, GitLab, and Bitbucket.

CI setup guide

Same six agents, same findings, wherever you run it.

More than a one-shot review

A model that writes a comment is the easy part. The workflow around it is what you are actually running.

🧠

Multi-agent review

Six agents run in parallel on one dimension each: security, performance, code quality, architecture, synthesis, and verification. Narrow briefs mean sharper findings.

# security-agent
Scanning for OWASP...
Finding: missing timeout
# perf-agent
Analysing loops...
O(n²) detected
⚖️

Contradiction detection

The synthesis layer catches where agents disagree and resolves it, so you don't read six reviewers arguing with each other.

🎯

Verified findings

Every finding is checked against the code and anchored to the right lines before it reaches you. Fewer misfires, less noise.

💬

Reply loop

On pull requests, Revue reads your replies to its comments and answers them instead of dropping feedback and going silent.

📜

Review history

Every run is logged, so you have a history across reviews, not a comment that scrolls away.

Real findings, not demos

This review came from running Revue on its own codebase. It flagged a missing HTTP timeout, proposed the exact fix in the PR comment, and verified the developer applied it.

Revue PR comment flagging a missing HTTP timeout with an inline fix suggestion
Screenshot shows Revue catching a medium-severity security issue in a GitHub PR, proposing a concrete code fix, and confirming the fix once applied.

Your model, your key, your code stays yours

🔑

Bring your own key

Use your own OpenRouter, OpenAI, Anthropic, or Azure key. You choose the model and you control the cost.

🔒

Revue never reads your code

Your diff goes straight to the provider you configure, with your key. Revue's servers only handle license validation and usage counts. No source code reaches us.

🧩

Works where you ship

GitHub, GitLab, and Bitbucket, local and CI, the same way.

Pricing that scales with your team

Free

$0

10 reviews/month

  • ✓ All 6 specialised agents
  • ✓ GitHub, GitLab & Bitbucket
  • ✓ Documentation & guides
Get started
Popular

Indie

$9/mo

100 reviews/month

  • ✓ All 6 specialised agents
  • ✓ GitHub, GitLab & Bitbucket
  • ✓ Email support
Get started

Pro

$29/mo

Unlimited reviews

  • ✓ All 6 specialised agents
  • ✓ GitHub, GitLab & Bitbucket
  • ✓ Priority support
  • ✓ Unlimited reviews
Get started
Feature Free Indie Pro
Reviews / month 10 100 Unlimited
Specialist agents All 6 All 6 All 6
Fix suggestions
BYOK
Custom rules (YAML)
Support Docs Email Priority

Review you control, on any model, before and after the push.

Start free, 10 reviews a month