1
AI code reviews on every pull request, in the IDE and from the CLI
8.4/10
What it does CodeRabbit is an AI code review service. When a pull request is opened, it analyses the change and posts a plain-language summary in the description, a walkthrough comment and line-by-line review comments, and you can reply to it in the thread to ask questions or request changes. Because it reviews the diff rather than the tool that… Read more →
Pros
- Catches real bugs agents introduce
- Works on any Git host
- Free for open source
Cons
- Can be noisy until tuned
- Per-developer pricing for private repos
Pricing: Free plan, paid from $30/mo · code review pull requests
🔥 Deal: Free reviews forever on public (open-source) repositories
2
Alibaba's AI code review CLI: deterministic pipeline plus LLM agent, line-level comments
★ 43k · +2.1k this week · Apache-2.0 · updated 2026-10-01
8.1/10
What it does Open Code Review (ocr) is an AI code review command-line tool open-sourced by Alibaba, where it began as the company's internal review assistant. It reads a Git diff, groups the changed files into review units and runs an LLM agent over each unit. The result is structured comments tied to exact lines. The design splits the work… Read more →
Pros
- Precise line-level comments with low token use
- Delegation mode lets your coding agent do the review with no extra API key
- CI recipes for GitHub, GitLab, GitFlic and Gerrit
Cons
- Tuned for precision, so recall is lower than general-purpose agents
- Diffs are sent to the LLM provider you configure
Pricing: Open source · code-review cli ci-cd llm git
3
AI code review graded against twelve classic engineering books, with citations and health scores
★ 1.5k · +6 this week · MIT · updated 2026-09-28
7.8/10
What it does Brooks Lint is an AI code-review pack that grades code against twelve classic software-engineering books rather than counting lines or cyclomatic complexity. It diagnoses six production-code "decay risks" (cognitive overload, change propagation, knowledge duplication, accidental complexity, dependency disorder, and domain-model distortion) and six matching test-suite risks. Every finding comes back in a fixed Symptom, Source, Consequence, Remedy… Read more →
Pros
- Consistent Symptom-Source-Consequence-Remedy findings with book citations
- Runs across many agents and in CI with SARIF output
Cons
- Only three platforms are maintainer-verified
- CI action sends your diff to the Anthropic API or a chosen endpoint
Pricing: Open source · code-review architecture tech-debt agent-skills ci
4
Stacked pull requests with an AI reviewer built in
7.7/10
What it does Graphite is a code review platform built around stacked pull requests: instead of one large pull request, you split a change into a chain of small, dependent ones that can be reviewed and merged in order. It adds its own review interface on top of GitHub, an AI reviewer called Graphite Agent and a merge queue that… Read more →
Pros
- Stacked PRs keep AI changes reviewable
- Fast review UI
Pricing: Free plan, paid from $20/mo · code review stacked prs
🔥 Deal: 20% off with annual billing
5
AI code review and governance agents for teams
7.6/10
What it does Qodo, formerly CodiumAI, is an AI code review and governance platform for engineering teams. It reviews pull requests inside your Git provider, posts summaries and structured findings, and enforces your organisation's coding standards. Its current documentation centres on the Qodo Review product rather than the test-generation tools it was first known for. What is inside / how… Read more →
Pros
- Reviews plus test generation
- Team rules
Pricing: Paid from $30/mo · code review testing
🔥 Deal: Free access for qualified open-source projects