| What it does | AI code review for GitHub that removes duplicate and low-confidence findings and posts one focused review
| Verification for code your AI agent writes
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| 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/
| Free: $0, 20 free reviews per month on public GitHub repos, no card required. Solo: $25/month ($20/month billed annually), includes 20 reviewed changes per month, private repo access, full reviewer catalog. Team: $25/user/month ($20 billed annually, 3 seat minimum), 20 reviewed changes per seat mont
|
|---|
| 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
| - Change-impact analysis showing callers, implementations, and removed code references
- Two independent reviewers (Codex and Claude) with parallel verification and reconciliation
- Five surfaces: MCP, CLI, Web, GitHub App, API
- MCP integration for agent verification before commit
- GitHub App for automatic pull request reviews
- Grounded findings with file, line, and evidence for each issue
- Per-review model selection on paid plans
- No repository connection required; only files from the agent are read
- Code review artifact retention and export
|
|---|
| 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
| - Checks code context outside the diff, not just the change itself
- Dual independent reviewer reconciliation catches contradictions humans need to judge
- Only grounded findings block; AI certainty is not enough
- Does not train on customer code and never will
- Integrates with coding agents before commit to catch issues early
|
|---|
| 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 | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 1 |
|---|
| Citation Flow (Majestic) | 22 | 25 |
|---|
| Referring domains (Majestic) | 56 | 20 |
|---|
PR Quorum
Veridu