Skip to content
SPECIFICTION
Get listed

AI Code Reviewer

github.com

Free plan Open source LinuxSelf-hosted
Visit github.com
Spec score 8.8 #7 of 47 in AI Code Review Tools

Spec sheet

What it does
AI Code Reviewer runs automated reviews on GitHub pull requests and posts findings back to the pull request.Read 21 Oct 2026 · github.com
Integrations
Documented OpenAI-compatible examples include DeepSeek, GLM, Kimi, Together, Groq, vLLM and LM Studio through a configurable base URL.Read 21 Oct 2026 · github.com
Security
The action reads pull-request diffs through the GitHub API and does not check out, build, or run pull-request code.Read 4 Oct 2026 · github.com
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.Read 21 Oct 2026 · chromewebstore.google.com
Configuration
Settings can be supplied in .github/ai-code-reviewer.yml or as action inputs, with action inputs taking precedence.Read 21 Oct 2026 · github.com
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.Read 21 Oct 2026 · github.com
Custom guidelines
A Markdown rules file can provide house style or framework conventions for reviews.Read 4 Oct 2026 · github.com
Custom rules
A Markdown rules_file can add repository-specific coding guidelines, and it is read from the base branch.Read 21 Oct 2026 · github.com
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.Read 4 Oct 2026 · github.com
Development quality bar
Contributor documentation specifies type checking, linting, Vitest tests, action builds and at least 80% coverage for all metrics.Read 21 Oct 2026 · github.com
Execution safety
The action reads diffs through the GitHub API and does not check out, build or execute pull-request code.Read 21 Oct 2026 · github.com
Incremental behavior
When incremental mode is enabled, a new push reviews only newly added commits and rerunning the same head SHA is skipped.Read 21 Oct 2026 · github.com
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.Read 21 Oct 2026 · github.com
Large-change handling
For very large pull requests the reviewer caps files or chunks and reports the truncation in its summary.Read 21 Oct 2026 · github.com
Licence
The repository is released under the MIT License, permitting reuse, modification, distribution and sale subject to retaining the notice and disclaiming warranty.Read 21 Oct 2026 · github.com
License and support
The project is MIT-licensed and welcomes contributions; the README does not state a paid support offering.Read 4 Oct 2026 · github.com
Limit: G2 CodeAnt listing
Reviews on that separate CodeAnt product mention stylistic nitpicks, cautious suggestions requiring manual adjustment and integration taking time.Read 21 Oct 2026 · g2.com
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.Read 21 Oct 2026 · producthunt.com
Maker identity
The GitHub account displays the name xiaofuqing and lists 48 repositories, six followers and one following.Read 21 Oct 2026 · github.com
Model providers
The action supports Anthropic Claude, OpenAI, local Ollama and OpenAI-compatible endpoints.Read 21 Oct 2026 · github.com
Notable limits
The default configuration skips reviews when more than 50 files change and caps inline comments at 20 per pull request.Read 4 Oct 2026 · github.com
Package status
The package manifest describes version 0.1.0, marks the workspace private and identifies the project as an MIT-licensed self-hosted GitHub pull-request reviewer.Read 21 Oct 2026 · github.com
Permissions
The example workflow requests contents read and pull-requests write permissions.Read 21 Oct 2026 · github.com
Praise: G2 CodeAnt listing
Reviews on the separately identified CodeAnt product praise accurate actionable findings, faster reviews and catching issues missed by linters.Read 21 Oct 2026 · g2.com
Privacy claim
The project says it operates without a vendor proxy and that Ollama on a self-hosted runner keeps code and diffs inside the user network.Read 21 Oct 2026 · github.com
Private repositories
The FAQ says private repositories can run reviews for collaborator branches because their workflows can access secrets.Read 21 Oct 2026 · github.com
Processing design
The action fetches pull-request diffs through the GitHub API, chunks files, makes structured model calls, filters and deduplicates findings, then posts comments.Read 21 Oct 2026 · github.com
Project popularity
The repository page showed zero stars, zero watchers and zero forks when accessed.Read 21 Oct 2026 · github.com
Public API and SDK
The published documentation exposes a GitHub Action interface and provider endpoint settings; it does not document a hosted public API or SDK.Read 21 Oct 2026 · raw.githubusercontent.com
Public-fork limitation
Reviews for fork pull requests in public repositories are skipped because GitHub withholds secrets from pull_request workflows triggered by forks.Read 21 Oct 2026 · github.com
Rating on Chrome Web Store
5.0 out of 5 from 1 rating, for an unrelated extension published by boring-ideas.com rather than this repository.Read 21 Oct 2026 · chromewebstore.google.com
Rating on G2
4.9 out of 5 from 5 reviews, but the G2 page identifies the product vendor as CodeAnt AI rather than xiaofuqing13.Read 21 Oct 2026 · g2.com
Rating on Product Hunt
5.0 out of 5 from 1 review, for a similarly named product launched in 2022 at ai-code-reviewer.com, not the GitHub repository.Read 21 Oct 2026 · producthunt.com
Review controls
Configurable controls include language, severity threshold, file inclusion and exclusion globs, a 20-comment default cap, a 50-file default cap, incremental review and fail-on-critical behavior.Read 21 Oct 2026 · github.com
Review output
Findings are inline comments tied to changed lines with severity, explanations and optional one-click suggestion blocks, plus a sticky summary comment.Read 21 Oct 2026 · github.com
Roadmap limits
Whole-repository deep mode, a self-hosted GitHub App, a local CLI and GitLab or Bitbucket support are listed as future roadmap items.Read 21 Oct 2026 · github.com
Runtime requirements
Contributor instructions require Node.js 20 or newer and pnpm 11 or newer; the package manifest specifies Node 22 or newer and pnpm 11.10.0.Read 21 Oct 2026 · github.com
Secret handling
Provider keys are expected through GitHub Secrets, are masked in logs and are not read from repository configuration.Read 21 Oct 2026 · github.com
Secrets
Provider API keys are passed through GitHub secrets, masked in logs, and not read from the repository configuration file.Read 4 Oct 2026 · github.com
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.Read 4 Oct 2026 · github.com
Workflow
It runs as a GitHub Action and can be added with a workflow file, without a server or checkout step.Read 4 Oct 2026 · github.com

Plans and prices

Free Free Free; users pay only their model-provider or compute costs Self-hosted GitHub Action · no per-seat charge · model usage billed separately Read 21 Oct 2026 · github.com

Every AI Code Reviewer plan and price →

Where Specifiction places it

Alternatives to AI Code ReviewerAll alternatives →