| What it does | Finds reproducible bugs and runtime vulnerabilities by running your product in a production-like sandbox
| Independent verification for AI agent outcomes
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | FR
| Not given
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Free for open source projects. Paid plans available for commercial use; specific pricing not listed.
| Hobbyist: free forever with 250 checks/month; Pro: $9/month with 2,500 checks/month, $0.01 per extra check
|
|---|
| Key features | - Builds a sandbox that replicates production environment
- Mocks or emulates third-party services like payments, mail and APIs
- Provides failing test for every defect found
- Maps product architecture and reads code for suspicions
- Validates security issues with real exploits against sandbox
- Crawls every link and finds missing routes
- Runs locally or in the cloud
| - Independent outcome verification with VERIFIED, FAILED, or UNKNOWN status
- First-party adapters for Stripe, GitHub, Linear, Sentry, Resend, and HTTP endpoints
- MCP integration with Claude Code, Cursor, and any MCP host
- GitHub Actions required check that fails on unverified claims
- Audit trail storing claims, evidence, and verdicts separately
- Capability inspection before agents call tools
- Read-only credential access with AES-256-GCM encryption
- Continuous monitoring with watches every 5-10 minutes on Pro plan
- Evidence retention for 7 days on Hobbyist, 1 year on Pro
|
|---|
| What makes it different | - Catches bugs code review misses by running the actual product instead of just reading diffs
- Every bug comes with a reproducible failing test that proves it
- Finds runtime vulnerabilities by firing real exploits against the sandbox
- Tests untested integrations and hard-to-mock async services
- Free for open source projects
| - Refuses to guess: returns UNKNOWN rather than false positives when evidence is unreachable
- Neutral gate between agent execution and success verification
- Runs the same way in production as in development
- Never needs write access, only reads authoritative state
- Structured audit trail for debugging and agent evaluation
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 25 ▲ +1 (up) since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 9 | 1 |
|---|
| Citation Flow (Majestic) | 27 | 23 |
|---|
| Referring domains (Majestic) | 63 | 14 |
|---|
heal
DidWork