Security & Testing AI Agents
Compare the best open-source AI agents for security & testing. Scanners, pentest helpers and test automation. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.
PentestPi
Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.
CyberPenda
Local-first pentest agent: Go daemon + React dashboard + Codex/Claude Code/Pi runtimes, scoped projects, Blackboard, sandbox runners
Toolguard
The "Cloudflare for AI Agents". 7-layer security interceptor, real-time observability dashboard, and automated reliability testing for MCP and AI tool chains. Prevent hallucinations, prompt injection, and destructive tool calls.
Agentegrity
The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.
List refreshed November 15, 2026. Data comes from public GitHub repositories.