XAIP demo
Trust Evidence Before Delegation
Not another agent framework. A portable signed receipt layer underneath them.
Agents often choose tools without inspecting any historical execution evidence.
Three candidate servers can all answer a task. They look interchangeable until you see the receipts behind them.
Without XAIP
With XAIP
Snapshot Static values shown above. Live precheck in progress…
XAIP does not make tools safe. It is not a sandbox, not an approval engine, and not a payment rail. It does not guarantee trust. It makes execution evidence visible before delegation.
Try it yourself
The SDK exposes the same evidence-before-delegation path with precheck():
import { precheck } from "xaip-sdk";
const result = await precheck({
task: "Store and retrieve user notes",
candidates: ["memory", "playwright", "unknown-server"]
});
Receipts come from MCP, LangChain.js, OpenAI-compatible tool-call loops, and other runtimes. The receipt format is provider-neutral.