Starter
Try AI PR review.
- 2 reviewers
- Code Review
- Security Review
- 3 seats included
- 15,000 credits to start, then 5,000/mo
- About 70 reviews to start, then about 25 a month
- Unlimited repos
Cursor writes the pull request; IonWarp reviews it on GitHub, alone or next to Bugbot, and hands each fix back to Cursor.
MediumKnown issue in the Code Review benchmark · caught by DeepSeek V4.1 FlashSee the graded case
Cursor's own code reviewer is Bugbot: it reviews pull requests, comments on likely bugs and hands fixes to the Cursor agent.[1] Cursor puts the average Bugbot run at $1.00–$1.50, depending on pull request size and complexity.[2] Cursor Bugbot pricing, worked out for a team.
On the same 50 open-source pull requests, Bugbot found 74 of 158 known issues and IonWarp's Code Review found 77, with more findings that matched none (78 to 56).[3] In Cal.com #14943 a cron job wrote retryCount + 1 from a stale read, so overlapping runs lost counts. IonWarp flagged it; Bugbot, Greptile and Qodo did not.[4]
Cursor facts are from Cursor's public pages, read on 2026-10-01 and 2026-10-02.
| Criterion | IonWarp | Cursor Bugbot |
|---|---|---|
| What it is | A GitHub app that reviews every pull request, adding security, performance and docs reviewers when the diff needs them | Cursor's pull request reviewer: it comments on potential issues and provides fixes in the Cursor editor[1] |
| Pricing | Workspace plans: Starter free; Pro $49/mo with 5 seats included | Usage-based billing; Cursor says the average run costs $1.00–$1.50, depending on PR size and complexity[2] |
| Git platforms | GitHub (GitHub Enterprise on the Enterprise plan) | GitHub, GitLab, Bitbucket and Azure DevOps[5] |
| Model | F1 | Precision | Recall | $ per review | Median time |
|---|---|---|---|---|---|
| DeepSeek V4.1 FlashThe model it runs | 49.2% | 49.7% | 48.7% | $0.10 | 6m 56s |
| Muse Spark 1.3A failed review retries on it · best on this benchmark | 56.6% | 65.3% | 50.0% | $0.42 | 3m 18s |
On this benchmark Muse Spark 1.3 scored higher than DeepSeek V4.1 Flash (56.6% F1 against 49.2%). Why IonWarp runs DeepSeek V4.1 Flash: on our own repositories from 1 to 21 September 2026 it filed slightly more P0 and P1 findings per 100 reviews than DeepSeek V4 Pro (14.8 on 549 reviews, against 13.5 on 104) for about a quarter of the cost ($0.034 a review against $0.140).
Measured on the same 50 open-source pull requests, with known issues. See the benchmark
Real IonWarp comments on open-source pull requests, graded against the benchmark's answer key.
Missed byQodo 18Greptile 25Cursor Bugbot 21CodeRabbit 20
4 of 47 · See the benchmark
Non-atomic retryCount increment loses retries on concurrent runs - update writes reminder.retryCount+1 from stale read; overlapping cron runs both write same value so delete threshold is delayed - should use atomic increment: data:{retryCount:{increment:1}} in both failure and catch updates · Code Review
HighKnown issue in the Code Review benchmark · caught by Muse Spark 1.3See the graded case
Public members template iterates bare members while guarding model - template guards on model but loops bare members, and route sets controller model only, so list can render empty · Code Review
HighKnown issue in the Code Review benchmark · caught by Muse Spark 1.3See the graded case
Silence notifications action does nothing for prom-only Grafana alerting rules - SilenceGrafanaRuleDrawer requires rulerRule but list passes only promRule, should render from promRule/identifier when rulerRule is absent or hide the item · Code Review
HighKnown issue in the Code Review benchmark · caught by Muse Spark 1.3See the graded case
readLength() returns -1 for 0x80; readSequence()/readInteger() pass it to readNext()/read() causing NegativeArraySizeException not IOException · Code Review
MediumKnown issue in the Code Review benchmark · caught by Muse Spark 1.3See the graded case
Muse Spark 1.3 is its best model on this benchmark; Code Review runs DeepSeek V4.1 Flash unless you pick another.
One workspace price with seats included. Credits pool across your team. Unlimited repos on every plan.
Try AI PR review.
Get AI PR review right from day 1.
Scale AI PR review.
Custom reviewers + credits · GitHub Enterprise · SSO/SAML + audit logs · Custom security review + SLA
No. Bugbot is Cursor's own reviewer, and any GitHub reviewer can review the same pull request. IonWarp installs as a GitHub app and reviews every pull request, whichever editor or agent wrote it.
Yes. Both post on the same pull request, and IonWarp's reviewers work independently of the editor that wrote the code.
Each finding includes an AI fix prompt. Paste it into Cursor's agent and push the fix; IonWarp re-reviews the pull request and updates the findings ledger.
No. IonWarp works on any GitHub repository, whatever editor or coding agent your team uses.
Email domain whitelist/blacklist regex is unanchored, allowing addresses like user@vaynermedia.com.attacker.tld to pass whitelist validation because it contains the substring @vaynermedia.com · Code Review