| What it does | AI code review for GitHub that removes duplicate and low-confidence findings and posts one focused review
| A harness for comprehension: understand code better and faster, especially code AI agents write
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| DE
|
|---|
| Pricing model | Not given
| Paid
|
|---|
| Pricing | Free: $0/month with 50 reviews/month across 2 repositories. Pro: $12/developer/month (or $9.60/month billed yearly) with 150 reviews/seat/month. Team: $25/developer/month (or $20/month billed yearly) with 300 reviews/seat/month. Max: $50/developer/month (or $40/month billed yearly) with 750 reviews/
| $15 a month, free for a month from the first launch. One subscription covers all your Macs. Billed monthly through Polar; cancel anytime in the customer portal.
|
|---|
| Key features | - Specialist reviewer panel with up to 8 templates plus custom reviewers
- Duplicate and low-confidence finding deduplication
- Repository-level policy configuration via .ai-review.yml
- Flexible model routing with OpenRouter integration
- Advisory-only reviews that never block merges
- Inline comments at exact diff positions
- Review modes: quiet, balanced, and paranoid confidence thresholds
- Cost dashboard and spend visibility
- Monthly review quotas with hard limits
- AES-256-GCM encryption for OpenRouter keys at rest
| - User journey visualization for pull requests showing blast radius and impact
- AI-generated flow diagrams from code using Claude
- Drill-down to actual code and methods behind each step
- Call graph visualization showing method relationships
- AI question answering about code steps using Claude
- Offline analysis for most languages with .NET SDK support for C#
- GitHub integration for private repository access
- Persistent layout between runs for consistent navigation
|
|---|
| What makes it different | - Brings your own OpenRouter key so you control models and data path instead of using shared keys
- Deduplicates findings across multiple reviewers to post only the strongest comments
- Advisory by design so maintainers always keep merge control
- Repository-level configuration to adjust review strictness for risky code paths
- One pooled monthly quota across team so review allowance scales with workspace size
| - Visualizes code as interactive maps with user journeys showing the full blast radius of changes
- Runs locally on your Mac with only Claude API calls going over the network
- AI-generated flow diagrams connect pull requests to actual business logic via real code methods
- Uses language-specific parsers for accurate code analysis instead of heuristics
- One subscription covers all your Macs with no signup or card required for first month
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 17 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 0 |
|---|
| Citation Flow (Majestic) | 22 | 18 |
|---|
| Referring domains (Majestic) | 56 | 18 |
|---|
PR Quorum
logPhase