Questions we get asked.

An AI security platform secures the whole request path of an LLM or agentic application at runtime - inspecting prompts, responses, streams, retrieved context, tool calls, and agent steps, and proving that coverage with evidence. ZNYX is an open-source AI security platform: a runtime AI firewall, agentic & MCP security, an output / data-loss gate, and audit-ready evidence (OWASP LLM Top-10 coverage, detector scorecards, ISO 42001 model cards) - self-hosted on every plan, so your data never leaves your boundary.

ZNYX ships 40 detectors behind a defense-in-depth engine: prompt injection and jailbreak, PII (65+ types, including checksum-validated regional IDs) with redaction, secrets and data exfiltration, toxicity / bias / sentiment, topic and competitor control, malicious URLs and phishing, insecure generated code, hallucination / groundedness (NLI-backed), system-prompt leakage, and agentic / MCP risks. Each runs through a deterministic → ML → LLM-judge ladder with a fail-closed scorecard gate.

ZNYX evaluates agent plans, individual agent steps, retrieved context, and memory writes; scans MCP / tool manifests for supply-chain risk (tool poisoning, dangerous permissions); checks embedding / vector integrity (OWASP LLM09); guards tool outputs against indirect injection; flags excessive agency; and enforces denial-of-wallet budgets on token, cost, and loop usage.

Guardrails are individual checks (e.g., a PII or jailbreak filter). An AI firewall is the inline enforcement layer that runs those checks on every request and decides to allow, block, redact, or mask in real time - including on streaming responses. ZNYX is the firewall and the engine behind it, plus the agentic, evidence, and release-safety layers that a single guardrail library does not provide.

No. The open-source runtime runs in your infrastructure, and an in-boundary inference sidecar lets ML and LLM-judge models run inside your VPC too. The optional hosted control plane is metadata-first by default - it sees trace ids, decisions, detector summaries, and latency, not prompt and response bodies. Enterprise can self-host the control plane as well for fully private, air-gappable deployment.

ZNYX generates an OWASP LLM Top-10 coverage scorecard mapped to your enabled detectors, per-detector scorecards (precision, recall, F1, AUROC, ECE, per-language breakdowns), and ISO 42001 / fairness / bias model cards, plus judge audit events. These give security and GRC teams audit-ready evidence for questionnaires, CISO reviews, and AI-governance frameworks such as ISO 42001, the EU AI Act, and the NIST AI RMF.

Yes - the runtime (the detection engine, detectors, and evaluation endpoints) is open source on GitHub, so you can inspect exactly what runs on your data. The hosted control plane (policy operations, evidence dashboards, traces) and enterprise deployment services are part of the commercial plans, and can also be self-hosted in Enterprise.

The open-source runtime is the data plane: the full detection engine, all 40 detectors, input/output/streaming/retrieval/agentic endpoints, the output-DLP gate, and six client SDKs. The control plane is the operations layer: policy management and safe rollout, traces and analytics, OWASP coverage and scorecards, the detector hub and policy playground, and SSO / SCIM / RBAC / GDPR tooling. Run the runtime alone, or add the control plane when teams need shared operations and evidence.

The runtime stays in your infrastructure on every plan, deployable via Docker, Docker Compose, or Kubernetes, with a Helm chart for Enterprise deployments. ZNYX is cloud- and model-neutral - it works with any provider, on-prem, or air-gapped.

No. The hosted operating model is metadata-first by default: hosted traces show identifiers, decisions, detector summaries, and latency rather than prompt and response bodies. Full-body retention is opt-in, and Enterprise can self-host the console entirely.

Start with the open-source runtime: self-hosted, unmetered, and no account needed. Add the hosted console when you want shared policy and evidence - Starter is its free tier at 10,000 evaluations a month, and Growth raises that allowance and adds team operations. Enterprise is for organizations needing fully private deployment, custom procurement, or written security commitments.

Not yet. Security and governance capabilities are implemented in the codebase today, but formal certifications, contractual SLAs, and published latency targets are on the roadmap rather than publicly attested. Reach out for Enterprise if you need a written commitment before published attestations are available.