LLM endpoint probe suite — 8 deterministic attack probes + replayable refusal classifier + multi-provider runner (OpenAI / Anthropic / Azure / ankr-proxy) + opt-in Agentic Control Center event bus. Extracted from xshieldai-asm-ai-module.

xShieldAI n8n community nodes — DAN gate, kernel enforcement, budget check, and audit log for AI agents.

Meta-package — installs the full xShieldAI Posture Suite (AEGIS + Agent Kernel + 4 primitives) in one shot + wireAllToBus() helper that connects all 4 primitives to a single SQLite event bus for the Agentic Control Center. Open-source counter to Fin Opera

Agent Kernel (formerly KavachOS) — seccomp-bpf + Falco kernel enforcement for AI agents. Core kernel-enforcement primitive of the xShieldAI Posture Suite.

HanumanG mandate primitives — Mudrika delegation credential verifier + 7-axis posture scorer (mudrika_integrity, identity_broadcast, mandate_bounds, proportional_force, return_with_proof, no_overreach, truthful_report) + opt-in Agentic Control Center even

Memory poisoning detection primitives for AI agents — pure pattern matchers (RAG trust, agent-role imperatives, tool-output poisoning, capability expansion, injection fingerprints) + opt-in Agentic Control Center event bus. Extracted from chitta-guard.

AEGIS / KavachOS — Agentic runtime governance: budget enforcement, DAN gate (human-in-loop), seccomp-bpf kernel enforcement, Falco anomaly detection + Agentic Control Center (cockpit page rendering all @rocketlang/* primitive events in one view, PRAMANA M

AEGIS Guard SDK — Five Locks primitives (approval-token, nonce, idempotency, SENSE, quality-evidence) + opt-in Agentic Control Center event bus for AEGIS-governed services