FAQ
Do I have to rewrite my agents?
Section titled “Do I have to rewrite my agents?”No. Guardyx governs the tool-call path, not your agent logic. Point an MCP client at a Guardyx endpoint (Quickstart) or wrap calls with the SDK — either way your existing agent stays as-is.
Is Guardyx a governance, risk, and compliance (GRC) product?
Section titled “Is Guardyx a governance, risk, and compliance (GRC) product?”No. Guardyx governs the runtime path agents use to act — the tool invocation path — not your company’s compliance posture. There are no questionnaires, no evidence collection, and no trust-center automation.
Which agent frameworks are supported?
Section titled “Which agent frameworks are supported?”Any agent that runs inside an MCP client, or whose tool calls you route through the SDK. Native adapters are confirmed for CrewAI, Microsoft AutoGen, Google ADK, the OpenAI Agents SDK, the Anthropic Claude Agent SDK, LangGraph, and raw OpenAI tool calling. LangChain tools are governed through the same LangGraph adapter. Anything else — including a custom Python agent — connects through the SDK.
How do approvals work?
Section titled “How do approvals work?”When a policy flags an action — for example, an external write above your auto-approve threshold — Guardyx blocks execution and routes it to a human reviewer. The action executes only after approval. The full decision is captured in the run trace.
How do I get access?
Section titled “How do I get access?”Start free — 5,000 governed calls a month, connectors included, for up to 3 teammates, with no card and no expiry. Paid plans and Enterprise, including self-hosted, are handled by request while we onboard design partners. See pricing.
Guardyx is free to start — 5,000 governed calls a month, connectors included, no card.