Secure your AI agent with one install command and fewer than 5 lines of code. No complex infrastructure or proprietary YAML required.
Run this single command in your project root. It will auto-detect your framework, install the needed dependencies, generate your policy file, and secure your agent.
npx suprawall init
Protected in 30 seconds
This command handles the installation and agent wrapping automatically. You do not need to read the manual steps below unless you require a highly custom execution flow.
Create an account and copy your SupraWall API key from the dashboard.
Your API key is ready
Prefix: sw_live_...
Native packages available for all major environments.
npm install suprawall
Set your security posture to 'Deny-by-default' for zero-trust protection.
import { Client } from "suprawall";
const client = new Client({
apiKey: process.env.SUPRAWALL_API_KEY,
defaultPolicy: "DENY" // Every action is blocked unless explicitly allowed
});Connect the security layer to your agent executor. Every tool call is now intercepted.
import { protect } from "suprawall";
// Wrap your existing agent (LangChain, Vercel AI, etc.)
const secured = protect(myAgent, { client });
// Execution is now gated by your policies
await secured.invoke({ task: "Delete production database" });Your agent is now bulletproof. Every blocked attempt generates a real-time audit log with a unique trace ID.
[2026-03-23 16:31:05] DENY tool:db.drop_table
Policy: restrict_db_operations
Trace ID: sup_7x2v1q9...
Policy evaluation is ultra-high performance, typically under 10ms. For agentic workflows which takes seconds to execute LLM calls, the impact is effectively zero.
Yes. Use our hosted Firebase cloud or bring your own Postgres, MySQL, or MongoDB via the Adapters architecture.
No. SupraWall lives in the execution layer. Your prompts remain yours — we only govern the tool outputs and inputs.