| What it does | AI-powered platform for automated web app and API penetration testing with replay-verified exploits
| Open-source security for AI coding agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | IN
| GR
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Pay Per Scan: 1 credit for $125, 5 credits for $545 ($109 each), 15 credits for $1,485 ($99 each), valid for 365 days. Professional: $199 per target/month or $1,999 per target/year. Enterprise: Custom pricing. Credits in INR: ₹6,999 for 1, ₹32,000 for 5 (₹6,400 each), ₹87,000 for 15 (₹5,800 each). P
| Open-source sensor is free. Enterprise pilot for up to 25 developer seats starts with a 90-day design-partner pilot, scoped with you.
|
|---|
| Key features | - Adaptive test planner that adjusts testing based on application behavior
- Authorization Matrix for multi-role privilege bypass detection
- DOM XSS source-to-sink analysis including React, Angular, and Vue framework sinks
- Sandbox proof-of-concept validation with sanitized exploits
- Attack chain escalation converting individual findings to business-impact paths
- LLM-driven login for SPA, OAuth, SAML, and MFA authentication
- CI/CD integration with quality gates for GitHub Actions, GitLab, Jenkins, CircleCI, Azure, Bitbucket
- OpenAPI, Postman, GraphQL, Protobuf, and WSDL API testing
- Compliance-mapped reports for PCI DSS 4.0, ISO 27001:2022, HIPAA, and GDPR
| - Records tool calls from Claude Code, Cursor, Codex, GitHub Copilot and other agents
- Detects risky sequences and agent behavior patterns
- Forwards to SIEM: Splunk, Elastic, Microsoft Sentinel, Google SecOps
- MCP server scanning to detect risky or malicious integrations
- Works on Windows, Linux and macOS without kernel driver
- DLP integration to prevent credential and sensitive data exfiltration
- 0 false positives across 57 test cases with MITRE ATT&CK coverage
|
|---|
| What makes it different | - Deterministic proof-of-concept exploits instead of probabilistic vulnerability flags
- Tests logic flaws and modern vulnerabilities beyond OWASP Top 10
- Sandbox-first design eliminates customer data exposure and production risk
| - Hash-chained records can be verified offline, catching any tampering or editing attempts
- Sees which AI agent ran the command and the session it belongs to, unlike EDR tools
- No account required, no telemetry sent until you configure a sink
- Single maintainer, self-funded, built in public with no hidden development
- All claims on the website verifiable by running commands on your own machine
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ● no change since last check | 36 ● no change since last check |
|---|
| Trust Flow (Majestic) | 5 | 5 |
|---|
| Citation Flow (Majestic) | 21 | 18 |
|---|
| Referring domains (Majestic) | 17 | 45 |
|---|
Pentrova
Agentmetry