AI Code Reviewer

Linux · Self-hosted

Freedom report

Two barsScore 6.4

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely1 of 6 device platforms
DocumentedPlans, terms and facts published

AI Code Reviewer is ranked #3 of 48 in AI code review tools on Freedom251. It runs on Linux, Self-hosted. There is a free plan.

AI Code Reviewer plans and pricing

All plans

Free Free You pay only your model provider’s usage; no other cost github.com · 4 Oct 2026

Compared on AI code review tools

Free plan: Yes
Security analysis: Yes
Custom review rules: Yes
Fix suggestions: Yes
Deployment model: self_hosted
Review trigger: automatic
Code hosts: GitHub

Best AI Code Reviewer alternatives

See all 12

Two bars CodeRabbit Free tier No. 1$0.40/mo6.7 Two bars ThinkReview Free tier No. 2$10/mo6.6 One bar Codacy Free tier No. 4$1.50/mo6.4 No signal CodeAnt AI Paid plans No. 5—6.4 One bar Gitar Free tier No. 6$20/mo6.4 One bar Greptile Free tier No. 7$30/mo6.4

The record

What it does: It reviews pull requests automatically and posts inline findings with severity, explanations, and applicable one-click suggestion blocks.
Workflow: It runs as a GitHub Action and can be added with a workflow file, without a server or checkout step.
Model providers: It supports Anthropic, OpenAI, local Ollama, and OpenAI-compatible endpoints.
Review output: It posts a sticky pull-request summary and inline comments anchored to changed lines.
Review controls: Settings include severity thresholds, file include and exclude patterns, incremental reviews, and a configurable maximum of 20 inline comments by default.
Custom guidelines: A Markdown rules file can provide house style or framework conventions for reviews.
Security: The action reads pull-request diffs through the GitHub API and does not check out, build, or run pull-request code.
Data handling: The project says it does not proxy requests through a service it runs; with Ollama on a self-hosted runner, code and diffs stay within the user’s network.
Secrets: Provider API keys are passed through GitHub secrets, masked in logs, and not read from the repository configuration file.
Permissions: The example workflow requests contents: read and pull-requests: write permissions.
Public fork limitation: Reviews of fork pull requests in public repositories are skipped because GitHub does not expose repository secrets to pull_request workflows from forks.
Notable limits: The default configuration skips reviews when more than 50 files change and caps inline comments at 20 per pull request.
Who it is for: The project presents itself as an open-source option for teams seeking self-hosting, model choice, and control over code privacy.
License and support: The project is MIT-licensed and welcomes contributions; the README does not state a paid support offering.
Price from: Free

Where it ranks on Freedom251

Best AI Code Review Tools in 2026#3 of 48

Is AI Code Reviewer yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote AI Code Reviewer

Sources

github.com/xiaofuqing13/ai-code-reviewer· checked 4 Oct 2026