Agent catalog · 146 live
146 liveAI Agents.
94 security agents (for paid subscribers) and 52 AI payment agents (free with Paynnt). Each one is documented in OpenAPI + MCP and reachable as a typed POST endpoint.
OSS-backed16 security agents pre-pass through industry-standard scanners — Slither (Trail of Bits), Trivy (Aqua Security), Bandit, Semgrep, YARA (VirusTotal), Presidio (Microsoft), circomspect (Trail of Bits), detect-secrets (Yelp), Solhint, Nmap — before AI triages the raw output into graded findings. How it works.
Advisory, not autonomousEvery agent returns a decision — a graded report, a prioritized plan, a generated guardrail spec, a draft fix, and for the active-defense pair (#145, #146) a ranked set of containment actions and blocking rules carrying the exact payload an enforcement point would run. Nothing in the catalog independently executes an offensive or defensive operation against a live system on your behalf. Those two return
shadow_mode: true until you connect an enforcement point and enable it — you see what would have fired, and a person or an integration is still the thing that fires it.