| What it does | Verification for code your AI agent writes
| A harness for comprehension: understand code better and faster, especially code AI agents write
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| DE
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | 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
| $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 | - 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
| - 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 | - 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
| - 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) | 2 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 0 |
|---|
| Citation Flow (Majestic) | 25 | 18 |
|---|
| Referring domains (Majestic) | 20 | 18 |
|---|
Veridu
logPhase