AI agents for security
9 tools · listed in dataset order, no ranking
AI agents that test applications you are authorized to assess, verify vulnerabilities, and propose fixes.
Strix
Strix (OmniSecure, Inc.)
Strix: Open-Source AI Pentesting Agents for Authorized App Security Testing
Best for: Engineering and AppSec teams that want open-source, AI-driven pentesting of their own apps and APIs in the CLI or CI, with an option to move to a managed platform
Shannon
Keygraph
Shannon: Open-Source White-Box AI Pentester for Web Apps and APIs
Best for: Engineering teams with access to both the source code and a staging copy of their web app or API who want open-source, evidence-backed security testing in CI
CodeMender
CodeMender: Google Cloud's AI Agent That Finds, Verifies, and Fixes Code Vulnerabilities
Best for: Security and platform teams already on Google Cloud who want an agent that verifies vulnerabilities and proposes tested patches, and who can join a preview program
Comp AI
Comp AI
Comp AI: Open-Source AI Compliance Platform for SOC 2, ISO 27001 and HIPAA
Best for: Startups and mid-market companies working toward SOC 2, ISO 27001, HIPAA or GDPR who want evidence collection and policy work automated, and engineering-led teams that value an open-source, self-hostable compliance platform
Codex Security
OpenAI
Codex Security: OpenAI's AI Agent for Finding, Validating, and Fixing Code Vulnerabilities
Best for: Security and engineering teams that already use Codex or the OpenAI API and want an agent that validates findings and prepares reviewable fixes, from a one-off repository audit to per-PR checks in CI
Google Mantis
Google Mantis: Open-Source Agent Skills for Finding, Reproducing, and Patching Vulnerabilities
Best for: Security engineers and AppSec teams who can operate isolated sandboxes and want a free, adaptable pipeline that reproduces and patches vulnerabilities with their own coding agent and models
Fleuret
Fleuret AI (FLEURET AI SAS)
Fleuret: EU-Hosted AI Pentesting Agents for Web Apps and APIs
Best for: European companies of roughly 50 to 1,000 people with a real web and API attack surface (SaaS, fintech, healthtech) and a NIS2, DORA, SOC 2 or ISO 27001 deadline, especially those that want pentest data and model inference kept on EU infrastructure
Hadrian
Hadrian Security B.V.
Hadrian: Agentic Attack Surface Management (Atlas) and On-Demand AI Pentesting (Nova)
Best for: CISO-led security teams at mid-market and enterprise organizations (Hadrian names 300 to 10,000 employees) with a large, changing internet-facing estate across cloud and on-premises, who want validated external exposures instead of scanner noise and pentest evidence for NIS2, DORA, ISO 27001 or SOC 2
OSS Scanner
Anthropic
OSS Scanner: Anthropic's Free, Opt-In AI Vulnerability Scanning Service for Critical Open-Source Projects
Best for: Core maintainers of established, security-critical open-source projects, such as libraries that process untrusted input, whose teams can already triage a steady flow of high and critical vulnerability reports and want them as early as possible
How to choose a security tool
Testing running apps vs fixing source code
Strix and Shannon test a running application (Shannon also reads its source code) and report issues they can validate. CodeMender works on source code: it verifies findings and drafts tested patches for developers to review. Codex Security also starts from the code, validating findings and preparing fixes without needing a running deployment. Google Mantis is an open-source set of skills and a reference harness that runs a similar source-first pipeline, from threat modeling to sandboxed reproduction and patching, with your own coding agent and models on your own infrastructure; Google says it is intended for demonstration, not production use. OSS Scanner is a free, opt-in service from Anthropic for core maintainers of security-critical open-source projects: it scans enrolled projects and emails reports with a reproducer and, where available, a candidate patch. Fleuret tests running web apps and APIs as a managed service with a flat price per app and data kept in the EU, for teams that want an outside pentest report rather than a tool to run themselves. Hadrian also works from the outside, for larger security teams: its agents continuously map internet-facing assets, confirm which exposures are exploitable, and run on-demand pentests of a single web app. Many teams will want both kinds of coverage.
Only test what you are authorized to test
Active security testing tools can change application state. Their vendors say to run them only against systems you own or have written permission to test, ideally a staging environment with disposable data.
Budget for model usage and run time
The open-source tools here are bring-your-own-model, so each scan incurs LLM costs, and deep runs can take hours. Managed platforms trade that for seat, per-test, or token-based pricing.
Common questions about security tools
What is an AI security agent?
An AI agent that performs security work such as testing an application you are authorized to assess, validating whether a vulnerability is real, or drafting a fix, rather than only listing potential issues.
Are there open-source AI pentesting tools?
Yes. Strix is Apache-2.0 and Shannon is AGPL-3.0. Both run locally or in CI with your own model provider, and both vendors also offer paid hosted platforms.
Do AI security agents replace human pentesters?
No. Vendors say findings still need human review, and coverage is narrower than a full manual assessment. They are best used for continuous or pre-release checks alongside periodic human-led testing.