# AI Choice Engine code review catalog

> Pull-request reviewers, not coding harnesses. HTML: https://aichoiceengine.com/ai-code-review

CodeRabbit, Qodo, Greptile, Gitar, Graphite, GitHub Copilot code review, and Cursor Bugbot. Unverified prices stay labelled.

## CodeRabbit

- Profile: https://aichoiceengine.com/ai-code-review/coderabbit
- Vendor: CodeRabbit
- Hosts: GitHub, GitLab, Bitbucket, Azure DevOps
- Surface: PR reviews, CLI, and IDE
- Pricing model: per-seat
- Pricing: Pro $24/user/month billed annually ($30 month-to-month); Pro Plus $48/user/month billed annually ($60 month-to-month); Enterprise custom. 14-day Pro+ trial, no card. Seats are billed for developers who create PRs, or assigned manually. Public repositories are free. Separate Security add-on $40/user/month; Slack agent $0.50 per agent minute.
- Hourly / throughput: Rolling per-developer hour, not a workspace bucket: Free 1 PR review/hour; default 14-day Pro+ trial 3/hour; Pro 5/hour; Pro+ 10/hour; Enterprise 12/hour. OSS public repos 1–10/hour by popularity. Incremental reviews after pushes count. Files per review (after path filters): Free/Pro 150, Pro+/Enterprise 300. Fair-usage can slow a developer at the 95th percentile of recent 7-day usage. A usage-based add-on can continue eligible over-limit reviews. @coderabbitai rate limit shows remaining capacity.
- Trial: 14-day Pro+ trial, no card. Trial throughput is 3 PR/IDE/CLI reviews per developer per hour — not the paid Pro+ 10/hour. Trial also caps 300 files per PR, 10 linked repos, 20 custom finishing-touch recipes, and 20 custom pre-merge checks.
- Config: CodeRabbit YAML / dashboard (reviews.auto_review and related)
- Inline comment cap: not verified
- Self-hosted option: yes
- Autofix: yes
- Merge gate: yes
- Best for: Teams on mixed git hosts; Orgs that want a dedicated reviewer with linters and issue trackers attached; Open-source maintainers who want free public-repo reviews
- Watch out: Per-seat pricing scales with PR authors, not with workspace. Pro’s hourly review cap is 5 per developer. Security scanning and Slack agent are billed separately. Confirm monthly vs annual toggle before quoting $24.
- Source: https://www.coderabbit.ai/pricing
- Verified: 2026-08-16

## Qodo

- Profile: https://aichoiceengine.com/ai-code-review/qodo
- Vendor: Qodo
- Hosts: GitHub, GitLab, Bitbucket, Azure DevOps
- Surface: PR review, IDE, and agent skills
- Pricing model: hybrid
- Pricing: Pro Team uses pooled credits at $0.012/credit. Packs: 2,500 / 5,000 / 20,000 credits (~18 / ~36 / ~144 reviews per month on Qodo’s own conversion). 14-day trial with unlimited credits, no card, no annual commitment on Pro Team. Enterprise is custom (SSO, BYOK, single-tenant or on-prem). Confirm current packaging on qodo.ai/pricing — seat vs credit mix can change.
- Hourly / throughput: No published per-developer hourly PR cap. The Pro Team pricing page states “No rate limits”; usage is pooled workspace credits with overage up to a configurable monthly spending cap. Docs also say reviews can skip until the next billing cycle if a monthly review limit is hit, and GitHub’s own hourly API rate limit can delay processing. After the trial, usage stops unless paid billing is active.
- Trial: 14-day trial with unlimited credits, no card. Trial is the initial state of every workspace, not a separate plan.
- Config: .pr_agent.toml, REVIEW.md, Qodo portal (finding_overflow_count default 3)
- Inline comment cap: not verified
- Self-hosted option: yes
- Autofix: not verified
- Merge gate: not verified
- Best for: Orgs that need enforceable coding standards across many repos; Teams mixing IDE review with PR review; Enterprises that want BYOK or on-prem options
- Watch out: Credit packs and the monthly spending cap drive the bill after the trial — the pricing-page “No rate limits” line is not the same as unlimited included reviews. Unused-credit rollover should be confirmed on the vendor FAQ. Do not confuse Qodo (qodo.ai, formerly CodiumAI) with Qodex (qodex.ai), which is an agentic QA platform.
- Source: https://www.qodo.ai/pricing/
- Verified: 2026-08-16

## Greptile

- Profile: https://aichoiceengine.com/ai-code-review/greptile
- Vendor: Greptile
- Hosts: GitHub, GitLab
- Surface: Full-repo context PR review
- Pricing model: hybrid
- Pricing: Starter: free, 1 active developer, 50 credits/month. Pro: $30/seat/month, 50 credits included per seat, then $1 per extra credit. 1 credit = 1 standard review; 3 credits = 1 TREX review. A seat is any developer who received a Greptile review in that billing period. 14-day Pro trial. Free for qualified MIT/Apache non-commercial OSS. 50% off for pre-Series A startups under $2M trailing-12-month revenue.
- Hourly / throughput: No published hourly cap. Starter: 50 credits/month for one active developer. Pro: 50 credits included per seat/month, then $1 per extra credit. One standard review uses 1 credit; one TREX review uses 3.
- Trial: 14-day Pro trial.
- Config: Custom rules (Pro)
- Inline comment cap: not verified
- Self-hosted option: yes
- Autofix: not verified
- Merge gate: not verified
- Best for: Teams whose defects are cross-file, not line-local; Solo developers who can live on the free 50-credit Starter cap; Early-stage startups that qualify for the 50% discount
- Watch out: Credits run out: 50 standard reviews per seat, then $1 each, and TREX burns three credits. GitHub and GitLab only on the public pricing page. Confirm TREX vs standard before comparing catch-rate anecdotes from third-party blogs.
- Source: https://www.greptile.com/pricing
- Verified: 2026-08-16

## Gitar

- Profile: https://aichoiceengine.com/ai-code-review/gitar
- Vendor: Gitar
- Hosts: GitHub, GitLab
- Surface: PR review plus CI fix loop
- Pricing model: per-seat
- Pricing: Core $20/user/month; Pro $40/user/month; both capped at 50 users. Enterprise custom, billed per PR rather than seats. 14-day Pro trial, no card. Annual billing advertised at 20% off. OSS public repos on GitHub/GitLab with an OSI-approved licence get Pro features free. PR summaries are free.
- Hourly / throughput: Manual “Gitar review” comments are unlimited. Core and Pro automatic-processing headroom (auto reviews and CI fixes) scales with assigned seats for the billing period; when it runs out, automatic reviews and fixes pause until the next period or you add seats. Vendor changelog: Pro gets double the per-seat review budget of Core — the numeric budget is not published. Enterprise: unlimited usage, no seat limits. REST API requests are rate-limited per organisation with an unpublished 429 threshold. After the 14-day trial, automatic processing stops; manual “Gitar review” still works.
- Trial: 14-day Pro trial, no card. Seats are not enforced during the trial — every member gets full automatic processing.
- Config: .gitar/review/*.md, .gitar/rules/*.md; also AGENTS.md, CLAUDE.md, .cursorrules
- Inline comment cap: not verified
- Self-hosted option: no
- Autofix: yes
- Merge gate: yes
- Best for: Teams that want CI failure analysis next to the review; Orgs willing to let a bot apply fixes until the pipeline is green; GitHub or GitLab shops evaluating a Sonar-owned reviewer
- Watch out: Sonar acquired Gitar on 2026-05-21. Vendor says standalone Gitar keeps shipping with no change for current customers, and deeper SonarQube integration is the roadmap — confirm DPA, support entity, and whether you are buying Gitar, SonarQube, or both. Core/Pro stop at 50 users and pause automatic reviews when seat headroom is exhausted. Merge blocking is Pro, not Core. GitHub.com only — GitHub Enterprise Server is not supported; self-hosted GitLab is an Enterprise git-host option, not a self-hosted Gitar.
- Source: https://gitar.ai/pricing
- Verified: 2026-08-16

## Graphite

- Profile: https://aichoiceengine.com/ai-code-review/graphite
- Vendor: Graphite
- Hosts: GitHub
- Surface: Stacked-PR inbox with bundled AI reviews
- Pricing model: per-seat
- Pricing: Hobby (personal repos, limited AI reviews), Starter, Team (unlimited AI reviews, customizations, merge queue), and Enterprise. Public pricing page advertises per-user monthly billing with 20% off annually. Exact dollar amounts were not shown in the 2026-08-16 HTML snapshot — confirm live figures on graphite.dev/pricing rather than copying third-party roundups.
- Hourly / throughput: No published hourly PR cap. Graphite’s pricing matrix lists AI reviews as Limited on Hobby and Starter, Unlimited on Team and Enterprise. Suggested fixes and CI summaries are on the paid matrix. Exact limited-tier counts were not shown on graphite.dev/pricing as of 2026-08-16.
- Trial: 30-day trial, or until you upgrade, whichever comes first. After that, unpaid personal repos fall back to Hobby.
- Config: AI review customizations (automation, filters, rules) — Team and Enterprise
- Inline comment cap: not verified
- Self-hosted option: not verified
- Autofix: yes
- Merge gate: not verified
- Best for: Teams already stacking PRs in Graphite; Orgs that want review, chat, and merge queue in one inbox
- Watch out: GitHub-only (GHES is an Enterprise feature). Limited AI reviews on Hobby/Starter — unlimited is a Team feature. Dollar amounts were not shown in the 2026-08-16 pricing HTML — confirm live figures on graphite.dev/pricing. Older ‘Diamond’ branding still appears in third-party roundups.
- Source: https://graphite.dev/pricing
- Verified: 2026-08-16

## GitHub Copilot code review

- Profile: https://aichoiceengine.com/ai-code-review/github-copilot-review
- Vendor: GitHub
- Hosts: GitHub, Azure DevOps (public preview)
- Surface: Built into GitHub.com pull requests
- Pricing model: bundled
- Pricing: Bundled with Copilot plans that include code review (Pro lists access to cloud agent and code review, with $15 monthly credits on Pro). Licensed-user review draws from the Copilot allowance. Orgs can enable review on PRs from people without a Copilot seat; that usage bills as GitHub AI Credits. From 2026-06-01, code-review workflows also consume GitHub Actions minutes.
- Hourly / throughput: No published hourly PR cap. GitHub docs estimate Lite reviews at $0.05–$1 of AI credits and Balanced at $0.25–$5, plus GitHub Actions minutes for agentic context gathering (self-hosted runners do not consume Actions minutes). Business/Enterprise reviews stop when the user or cost-center budget is exhausted. Copilot also has unpublished temporary rate limits during high demand. Copilot Free does not include code review.
- Trial: Follows the Copilot plan trial, not a separate reviewer trial.
- Config: .github/copilot-instructions.md, .github/instructions/*.instructions.md, AGENTS.md, .github/skills/; org/repo automatic-review policies
- Inline comment cap: not verified
- Self-hosted option: no
- Autofix: yes
- Merge gate: not verified
- Best for: Teams standardised on GitHub Copilot; Orgs that want review coverage on every PR without a seat for every author
- Watch out: Shares credit pools with the rest of Copilot. Unlicensed-author coverage is policy-gated and bills AI Credits plus Actions minutes. Azure DevOps support is public preview. Buying a dedicated reviewer only pays if Copilot’s native review is too shallow for the repo.
- Source: https://github.com/features/copilot/plans
- Verified: 2026-08-16

## Cursor Bugbot

- Profile: https://aichoiceengine.com/ai-code-review/cursor-bugbot
- Vendor: Cursor
- Hosts: GitHub, GitLab, Bitbucket, Azure DevOps (limited)
- Surface: PR check plus Cursor editor fixes
- Pricing model: usage-based
- Pricing: Usage-based since the May 2026 change (legacy $40/seat plans renew onto usage billing after 2026-06-08). Individuals consume included usage then on-demand; Teams bill from on-demand spend. Cursor Pro ($20/mo) lists Bugbot on usage-based billing; Teams ($40/user/mo) lists agentic code reviews with Bugbot. Cursor’s May 2026 blog: average run $1.00–$1.50 depending on PR size — that is a vendor average, not a published per-run list price. Confirm live rates at cursor.com/pricing#bugbot. 14-day free trial on the product page.
- Hourly / throughput: No published hourly PR-review cap. Bugbot API: most endpoints 60 requests/minute per team; POST /bugbot/review 30/minute; dry-run 10/minute. Reviews first consume included usage (Individuals) or on-demand spend (Teams). Autofix uses Cloud Agent credits at plan rates. Higher effort levels cost more usage.
- Trial: 14-day free trial on all plans (product page).
- Config: .cursor/BUGBOT.md; team/repo rules (30k chars each, 100k combined per review)
- Inline comment cap: not verified
- Self-hosted option: no
- Autofix: yes
- Merge gate: yes
- Best for: Teams already on Cursor who want a PR gate without a second vendor; Repos where logic bugs matter more than nits
- Watch out: Not a substitute for choosing Cursor the editor — that comparison lives under /ai-harnesses. Usage billing means a busy repo can outrun a flat-seat mental model; size spend from cursor.com/pricing#bugbot, not from a third-party $/run table. Requiring the Bugbot check without fail-on-unresolved-issues still allows merge when findings are posted.
- Source: https://cursor.com/bugbot
- Verified: 2026-08-16