- Home
- AI Code Review Tools
- AI Code Reviewer
AI Code Reviewer
What it is
AI Code Reviewer automatically reviews GitHub pull requests and posts a summary with inline findings on changed lines. Findings can include severity, explanations, and one-click suggestion blocks. The tool runs as a GitHub Action configured through a workflow file, without a server or checkout step. It supports Anthropic, OpenAI, local Ollama, and OpenAI-compatible endpoints. Teams can set severity thresholds, choose file include and exclude patterns, enable incremental reviews, and add house style or framework conventions in a Markdown rules file. The action reads diffs through the GitHub API and does not check out, build, or run pull-request code. Provider keys are passed through GitHub secrets and masked in logs. 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. The MIT-licensed project is free, though model-provider usage may cost money. By default, reviews skip changes affecting more than 50 files and allow up to 20 inline comments. Reviews of public-repository fork pull requests are skipped because those workflows cannot access repository secrets.
For and against
For
- Runs as a GitHub Action without a server or checkout step
- Supports Anthropic, OpenAI, Ollama, and compatible endpoints
- Markdown rules can specify house style or framework conventions
- Does not check out, build, or run pull-request code
Against
- Reviews skip changes affecting more than 50 files by default
- Inline comments are capped at 20 per pull request
- Public-repository fork pull requests are skipped
- Model-provider usage may cost money
The verdict
AI Code Reviewer offers configurable automated reviews within a GitHub workflow, with multiple model options and controls for code handling. Its file-count threshold, comment cap, and fork limitation may affect how teams use it.
Who it suits
It suits teams looking for an open-source GitHub pull-request reviewer with model choice and self-hosting options. Teams using public-repository forks should note that those pull requests are skipped.
Plans and prices
Free
Self-hosted GitHub Action · no per-seat charge · model usage billed separately
Read 21 Oct 2026 · github.com
On the record
- Chrome extension details
- The unrelated Chrome listing reports eight users, version 0.0.5, 346 KiB size and an update date of February 21, 2026.chromewebstore.google.com · read 21 Oct 2026
- Configuration
- Settings can be supplied in .github/ai-code-reviewer.yml or as action inputs, with action inputs taking precedence.github.com · read 21 Oct 2026
- Cost example
- The FAQ estimates roughly $0.05–$0.20 per typical pull request with Claude Sonnet, a few cents with Haiku and zero model charge with local Ollama apart from compute.github.com · read 21 Oct 2026
- Custom guidelines
- A Markdown rules file can provide house style or framework conventions for reviews.github.com · read 4 Oct 2026
- Custom rules
- A Markdown rules_file can add repository-specific coding guidelines, and it is read from the base branch.github.com · read 21 Oct 2026
- 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.github.com · read 4 Oct 2026
- Development quality bar
- Contributor documentation specifies type checking, linting, Vitest tests, action builds and at least 80% coverage for all metrics.github.com · read 21 Oct 2026
- Execution safety
- The action reads diffs through the GitHub API and does not check out, build or execute pull-request code.github.com · read 21 Oct 2026
- Incremental behavior
- When incremental mode is enabled, a new push reviews only newly added commits and rerunning the same head SHA is skipped.github.com · read 21 Oct 2026
- Installation
- Installation consists of adding a GitHub Actions workflow using xiaofuqing13/ai-code-reviewer@v1 and a provider secret; checkout and a separate server are not required.github.com · read 21 Oct 2026
- Integrations
- Documented OpenAI-compatible examples include DeepSeek, GLM, Kimi, Together, Groq, vLLM and LM Studio through a configurable base URL.github.com · read 21 Oct 2026
- Large-change handling
- For very large pull requests the reviewer caps files or chunks and reports the truncation in its summary.github.com · read 21 Oct 2026
- Licence
- The repository is released under the MIT License, permitting reuse, modification, distribution and sale subject to retaining the notice and disclaiming warranty.github.com · read 21 Oct 2026
- License and support
- The project is MIT-licensed and welcomes contributions; the README does not state a paid support offering.github.com · read 4 Oct 2026
- Limit: G2 CodeAnt listing
- Reviews on that separate CodeAnt product mention stylistic nitpicks, cautious suggestions requiring manual adjustment and integration taking time.g2.com · read 21 Oct 2026
- Limit: Product Hunt name collision
- Product Hunt discussion for the unrelated product reports single-file or text-box-only review, missed async/await errors, client-side exceptions and long-code formatting problems.producthunt.com · read 21 Oct 2026
- Maker identity
- The GitHub account displays the name xiaofuqing and lists 48 repositories, six followers and one following.github.com · read 21 Oct 2026
- Model providers
- The action supports Anthropic Claude, OpenAI, local Ollama and OpenAI-compatible endpoints.github.com · read 21 Oct 2026
