# farol — AI Coding Tool Review & Pricing

> farol is a CLI and GitHub Action that runs after your AI code review and tells the person who approves a pull request how risky the merge is and where the risk lives. It uses the real compilers to trace what the change reaches and produces a deterministic risk score, verdict and file ranking.

Source: https://ai.dosa.dev/tools/farol · Updated Oct 26, 2026 · Category: AI Code Review & Security · Published by dosa.dev

## At a glance

- **Tool**: farol
- **Company**: Winnin
- **Category**: [AI Code Review & Security](https://ai.dosa.dev/category/code-review)
- **Pricing model**: Open Source
- **Official website**: https://winnin.github.io/farol/

## Key features

- Declaration graph built with the TypeScript type checker, go/types and Python ast to list every page, endpoint, RPC method, job and script a change reaches
- Deterministic verdict (fast track, quick review, careful review) and a 0-100 risk score from reach, diff coverage, security findings, contract breaks and dependency changes
- Contract-break detection for GraphQL, FastAPI, Go handlers and gRPC, with the services that call each endpoint
- Interactive HTML report and PR comments with full and since-last-push incremental reports
- Fails closed as unknown, never executes or uploads your code and never blocks a merge

## Pricing

**Model**: Open Source

Free and open source under the MIT license; no account or hosted service, it runs locally or in your own CI runner.

## Who it is for

- **Best for**: Teams merging a high volume of agent-written pull requests in TypeScript, Go or Python who want human review attention focused on the riskiest changes.
- **Not ideal for**: Projects in languages other than TypeScript, Go and Python, or teams looking for an AI reviewer that comments on individual lines, which farol is designed to complement rather than replace.

## Verdict

A thoughtful, deterministic complement to AI code review that makes the human approval step in agentic workflows faster and safer.

## Recent updates

Launched as a Show HN in October 2026; v0.2.0 on October 26, 2026 turned the HTML report into a review workbench.

## Frequently asked questions

### Is farol free?

Yes - farol is Open Source. Free and open source under the MIT license; no account or hosted service, it runs locally or in your own CI runner.

### Is farol open source?

Yes - farol is open source. Free and open source under the MIT license; no account or hosted service, it runs locally or in your own CI runner.

### Who is farol best for?

Teams merging a high volume of agent-written pull requests in TypeScript, Go or Python who want human review attention focused on the riskiest changes.

### Who is farol not ideal for?

Projects in languages other than TypeScript, Go and Python, or teams looking for an AI reviewer that comments on individual lines, which farol is designed to complement rather than replace.

### What are the best farol alternatives?

The closest farol alternatives on ai.dosa.dev are CodeRabbit, Qodo, Snyk Code - all listed under AI Code Review & Security.

### Who makes farol?

farol is developed by Winnin. It is listed in the AI Code Review & Security category on ai.dosa.dev.

## Top alternatives

- [CodeRabbit](https://ai.dosa.dev/tools/coderabbit) (Paid) — Engineering teams needing to manage high-volume pull request pipelines, automate security and quality gates, and prioritize review queues efficiently.
- [Qodo](https://ai.dosa.dev/tools/qodo-qodo) (Freemium) — Enterprise engineering teams and organizations that need to maintain code quality, security, and governance standards while scaling the use of AI-driven development tools across large or complex codebases.
- [Snyk Code](https://ai.dosa.dev/tools/snyk-code-snyk) (Freemium) — Developers and security teams looking to integrate automated security scanning and remediation directly into their existing coding workflow.
- [cubic](https://ai.dosa.dev/tools/cubic) (Freemium) — Development teams using GitHub who need automated, context-aware code reviews that integrate with internal coding standards and support complex refactors.
- [Kodus](https://ai.dosa.dev/tools/kodus) (Freemium) — Engineering teams seeking an open-source, flexible, and privacy-focused code review solution with full control over AI model selection and costs.
- [Gito](https://ai.dosa.dev/tools/gito) (Open Source) — Engineering teams prioritizing data privacy and vendor neutrality, open-source maintainers, and developers seeking automated, consistent code quality checks.
- Full alternatives guide: https://ai.dosa.dev/tools/farol/alternatives