AI security audits for e-commerce and web platforms
Open-source security for AI coding agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
FR
GR
Pricing model
Not given
Open source
Pricing
Security audit: €500 per audit (managed service by AgentRidge team). Vulnerability remediation: €500 per service (separate offering after audit). Software licence: €2,000 per year (unlimited audits, local Mac and Windows software).
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
Real-time CVE exploitation for always-on red teaming
Zero-setup intelligence that works out of the box
Autonomous attack chains from signal to proof
Business-logic focused, not noise-driven
Evidence-first results you can reproduce
Agentic workflows you control
200+ professional tools supported
Local Mac and Windows software
PDF reports with evidence and reproduction steps
Access to tested scope including authenticated workspaces
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
Runs locally on your computer, not in the cloud
Focuses on business-critical vulnerabilities, not noise
Provides visual evidence and reproduction steps for every finding
Explores authenticated areas and business workflows
Includes support and remediation services with audits
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
AgentRidge
Agentmetry