Skip to content
SPECIFICTION
Get listed

Revue

revue.sh

From $9/mo Free plan WebWindowsLinuxAPI
Visit revue.sh
Spec score 8.6 #11 of 48 in AI Code Review Tools

What it is

Revue is a multi-agent AI code reviewer for local changes and pull requests. Its Claude Code skill reviews staged changes, while CI mode can review pull requests or merge requests on GitHub, GitLab, and Bitbucket and post findings as inline comments. Six specialist agents cover security, performance, code quality, architecture, synthesis, and verification. Revue says it checks findings against the code and anchors them to relevant lines. Users supply their own AI provider API key; listed providers include OpenRouter, Anthropic, OpenAI, Azure OpenAI, and custom OpenAI-compatible endpoints. For local reviews, code runs in the user’s environment and source code is not received, stored, or processed by Revue’s servers. The service may log code-change metadata, review counts, timestamps, repository and platform metadata, and diagnostic data. The default diff limit is 2,000 lines and can be raised in.revue.yml. Windows support requires WSL2; there is no native Windows build, and Windows on ARM is unsupported. Free costs nothing, with unlimited reviews for 30 days and 10 per month afterward. Indie is $9 a month; Pro is $29 a month.

Spec sheet

Product
Revue is a multi-agent AI code reviewer that operates locally through Claude Code and in CI pipelines.Read 21 Oct 2026 · revue.sh
Intended users
The site describes local reviews before committing and CI reviews for teams that want pull requests reviewed automatically.Read 8 Oct 2026 · revue.sh
Support
The pricing page lists documentation for Free, email support for Indie, and priority support for Pro.Read 8 Oct 2026 · revue.sh
AI providers
Supported provider choices include OpenRouter, Anthropic, OpenAI, Azure OpenAI, and custom OpenAI-compatible endpoints.Read 21 Oct 2026 · revue.sh
Bring your own key
Revue requires users to provide their own AI provider API key and says it does not provide a shared AI backend.Read 8 Oct 2026 · revue.sh
BYOK
Users must supply their own AI-provider API key and therefore control provider selection and inference spending.Read 21 Oct 2026 · revue.sh
CI installation
CI setup installs the revue-ci Python package and uses repository secrets or variables for license and AI keys.Read 21 Oct 2026 · revue.sh
CI workflow
Revue can automatically review pull requests or merge requests in GitHub Actions, GitLab CI/CD, and Bitbucket Pipelines.Read 21 Oct 2026 · revue.sh
Cloud data processors
The privacy policy names Stripe, Brevo, Cloudflare, and Fly.io as service subprocessors.Read 21 Oct 2026 · revue.sh
Code handling
For local reviews, the privacy policy says code review runs in the user's environment and source code is not received, stored, or processed by Revue's servers.Read 8 Oct 2026 · revue.sh
Configuration depth
The configuration reference documents provider, model, endpoint, temperature, token limits, review behavior, noise filters, agents, and output settings.Read 21 Oct 2026 · revue.sh
Contradiction detection
A synthesis layer is intended to resolve disagreements between specialist agents.Read 21 Oct 2026 · revue.sh
Custom rules
Repositories can define custom review behavior in a .revue.yml file.Read 21 Oct 2026 · revue.sh
Data collected
The privacy policy says Revue may log code-change metadata, review counts, timestamps, repository and platform metadata, and diagnostic data.Read 8 Oct 2026 · revue.sh
Data handling
For local execution, Revue says source code stays on the user's machine and only activation metadata and aggregate usage counts reach Revue servers.Read 21 Oct 2026 · revue.sh
Diff limit
The default review limit is 2,000 unified-diff lines, adjustable through .revue.yml.Read 21 Oct 2026 · revue.sh
Fix suggestions
Paid tiers can post platform-native code suggestions when the resolver generates a sufficiently confident scoped fix.Read 21 Oct 2026 · revue.sh
Free quota behavior
After the initial unlimited period, the Free tier allows 10 reviews per calendar month and returns a 429 response after the limit.Read 21 Oct 2026 · revue.sh
Independent identity warning
The Chrome Web Store listing named RevueAI is a separate GitHub PR review extension by Billmike, not the revue.sh service.Read 21 Oct 2026 · chromewebstore.google.com
Independent repository status
The separate Billmike/revue-ai GitHub repository describes a Chrome extension and shows 1 star and 0 forks.Read 21 Oct 2026 · github.com
Intent drift
Revue compares acceptance criteria in a pull-request description with the changed code and reports per-criterion alignment or contradiction.Read 21 Oct 2026 · revue.sh
Licence model
The terms grant a limited, non-exclusive, non-transferable internal-use licence and state that Revue retains ownership of the service and findings.Read 21 Oct 2026 · revue.sh
Local workflow
Users install the /revue Claude Code skill and run reviews on staged diffs before committing.Read 21 Oct 2026 · revue.sh
Logged metadata
Revue may log repository and platform metadata, review counts, timestamps, diagnostics, and code-change metadata such as filenames and line counts.Read 21 Oct 2026 · revue.sh
Maker launch timing
LinkedIn describes Revue.sh as a solo-built project started in March 2026 and publicly launched on 10 June 2026.Read 21 Oct 2026 · uk.linkedin.com
Maker legal identity
The service is operated by Daniel Sánchez Cisneros, a UK sole trader trading as Revue.Read 21 Oct 2026 · revue.sh
No public SDK stated
The opened official documentation describes CLI, CI package, configuration, and provider integrations but does not document a public SDK or self-hosted deployment.Read 21 Oct 2026 · revue.sh
Pull request workflow
In CI, Revue can review pull requests on GitHub, GitLab, and Bitbucket and post findings as inline comments.Read 8 Oct 2026 · revue.sh
Rating on Chrome Web Store
The separate RevueAI extension is rated 0 out of 5 from 0 ratings.Read 21 Oct 2026 · chromewebstore.google.com
Refund limitation
Subscription charges are generally non-refundable after billing, with exceptional refunds left to Revue's discretion.Read 21 Oct 2026 · revue.sh
Reply loop
On pull requests, Revue reads replies to its comments and responds in the review thread.Read 21 Oct 2026 · revue.sh
Review agents
Six specialist agents cover security, performance, code quality, architecture, synthesis, and verification.Read 21 Oct 2026 · revue.sh
Review history
Each review run is logged so teams retain a history across reviews.Read 21 Oct 2026 · revue.sh
Service limitation
Revue disclaims guarantees that the service is uninterrupted, secure, error-free, or that findings catch every bug or security issue.Read 21 Oct 2026 · revue.sh
Verified findings
The product says findings are checked against the code and anchored to relevant lines before delivery.Read 21 Oct 2026 · revue.sh
Windows ARM limitation
Windows on ARM is unsupported because Revue does not publish a Linux aarch64 build.Read 21 Oct 2026 · revue.sh
Windows requirements
Windows use requires WSL2 on 64-bit Intel or AMD hardware; there is no native Windows build.Read 21 Oct 2026 · revue.sh
Windows support
Windows is supported through WSL2; the installation guide says there is no native Windows build and Windows on ARM is unsupported.Read 8 Oct 2026 · revue.sh

Plans and prices

Free Free 30 days unlimited; then 10 reviews/month forever All 6 agents · GitHub, GitLab & Bitbucket · Documentation & guides · no fix suggestions Read 21 Oct 2026 · revue.sh
Indie $9 a month $9/mo 100 reviews/month · All 6 agents · GitHub, GitLab & Bitbucket · fix suggestions · email support Read 21 Oct 2026 · revue.sh
Pro $29 a month $29/mo Unlimited reviews · All 6 agents · GitHub, GitLab & Bitbucket · fix suggestions · priority support Read 21 Oct 2026 · revue.sh

Every Revue plan and price →

Strong points and limits

Strong points

  • Six agents review distinct code concerns.
  • Findings are checked against code and tied to lines.
  • CI reviews support GitHub, GitLab, and Bitbucket.
  • Local reviews keep source code on the user's environment.
  • Paid plans include fix suggestions.

Limits

  • Free reviews fall to 10 per month after 30 days.
  • Users must supply their own AI provider API key.
  • Windows requires WSL2; Windows on ARM is unsupported.
  • Default diff limit is 2,000 lines.

Who it suits

Revue suits developers seeking reviews of staged changes before committing or teams wanting automated pull-request reviews. It requires an AI provider key supplied by the user.

Verdict

Revue offers both local and CI review workflows, with a free allowance that changes after its first 30 days. Check the diff limit, Windows requirements, and plan quota against your workflow.

Where Specifiction places it

Alternatives to RevueAll alternatives →