| What it does | Secure AI agents, with evidence
| AI writes your code. Canary tests it.
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | GR
| US
|
|---|
| Pricing model | Freemium
| Contact for pricing
|
|---|
| Pricing | Community: €0 (open source, 1x monthly testing volume, weekly monitoring, 3 seats, 30-day data retention). Team: €349/mo (20x monthly testing volume, 10 seats, 90-day data retention, webhooks, priority support). Enterprise: Custom pricing (contact for details).
| Not given
|
|---|
| Key features | - Automated adversarial testing with multi-turn and agentic attack chains
- Black-box testing without SDK installation or agent modification
- Four-tier Humanbound Firewall with LLM judge
- Continuous posture score from 0 to 100
- Framework mapping to EU AI Act, NIST AI RMF, OWASP LLM Top 10, OWASP Agentic AI Top 10
- Air-gapped testing with self-hosted models like Ollama
- Export compliance evidence in HTML, PDF, JSON, SARIF, CEF formats
- Webhook integration with SIEM and ticketing systems
- Apache-2.0 open source CLI, testing engine, and SDK
- Baseline campaign completion in hours
| - Automatic test generation from code diffs
- Sandbox app testing with real browsers and APIs
- Reproduced failures with root causes
- Automatic regression test creation
- GitHub PR integration with inline comments
- Testing at every development step
- Support for multiple coding agents
- Slack and Linear integration
- Comprehensive test reports with evidence
- CLI for local testing before commits
|
|---|
| What makes it different | - Continuous monitoring instead of point-in-time reports
- Adaptive multi-turn attack chains that evolve over time
- Same open-source code as platform with nothing held back or limited
- No account required for local open-source testing
- Framework mapping and compliance evidence for regulatory requirements
| - Catches bugs in AI-generated code automatically before they reach production
- Tests code in real browsers and APIs, not just unit tests
- Automatically converts findings into lasting regression tests
- Works directly inside coding agents with one-line integration
- Provides proof with replays and root causes for every failure
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 14 ▲ +1 (up) since last check | 18 ● no change since last check |
|---|
| Trust Flow (Majestic) | 8 | 5 |
|---|
| Citation Flow (Majestic) | 30 | 32 |
|---|
| Referring domains (Majestic) | 71 | 150 |
|---|
Humanbound