Zero trust firewall for AI agents

Your agents act.
You stay in control.

Jitex validates every tool call your AI agents make — checking intent against policy, blocking dangerous actions, and routing high-risk operations to a human. Your keys never leave your machine.

Free forever · No credit card required · Running in 5 minutes

Zero
Keys sent to our servers
4-tier
Intent evaluation depth
100%
Tool calls audited
1-tap
Human approval from your phone

Agents have access. Nothing checks what they do with it.

Every tool call is an unvalidated action. One prompt injection, one hallucination, one bad reasoning chain — and your agent acts on your behalf without asking.

Without Jitex
  • Agent tools execute with zero validation
  • One prompt injection = uncontrolled access
  • No visibility into what the agent actually called
  • No way to pause or cancel a runaway agent
  • Audit log: a blank page
With Jitex
  • Every tool call validated against policy before execution
  • Prompt injection blocked — dangerous patterns auto-denied
  • Every tool invocation logged with intent + verdict
  • High-risk calls paused for 1-tap human approval
  • Cryptographic audit trail, exportable for compliance

Zero trust. Every layer.

Traditional security assumes trust after authentication. Jitex validates every single action — no implicit trust, ever.

Intent Validation

A 4-tier evaluation engine scores every tool call — pattern matching, deterministic rules, embedding similarity, and an LLM guardrail. Dangerous actions are blocked before they execute.

Every Action Audited

Every tool call is cryptographically logged — tool, parameters, verdict, and reasoning. Immutable. Exportable. Compliance-ready.

Keys Never Leave

The proxy runs in your environment so credentials never leave your machine. Only intent metadata — tool name, parameters, reasoning — reaches the Jitex API. Never tokens, never secrets.

One-Line SDK

Works with LangChain, CrewAI, PydanticAI, Vercel AI SDK, and plain fetch.

// Wrap any tool const safe = jitex(myTool)

One-Tap HITL

High-value or suspicious calls are suspended and routed to you via push, Slack, or email. Approve in one tap.

Approval required
4:51 PM
Toolstripe.refunds.create
Amount$2,400.00
Confidence62% — low

Running in 5 minutes

From zero to validated agent in one terminal session.

01

Install the proxy

One package. The proxy sits in your environment so your keys never leave. We only see intent metadata — never secrets.

$ npx @jitex/proxy
02

Wrap your tools

Add one line to your agent. Jitex validates intent, enforces policy, and blocks dangerous actions.

const safe = jitex(myTool)
03

Stay in control

Every action is logged. High-risk calls pause for your approval. Full audit trail at all times.

Works with your stack

Validate every API your agent touches. Framework-agnostic, provider-agnostic.

Stripe
GitHub
Slack
AWS
Linear
Notion
Salesforce
HubSpot
Twilio
SendGrid
Shopify
Any HTTP API
Compliance-ready architecture

Built for regulated industries

Immutable audit logs, human approval gates, policy enforcement, and local execution give your compliance team everything they need — out of the box.

SOC 2

Immutable audit logs, access controls, and continuous monitoring map directly to SOC 2 Trust Service Criteria.

HIPAA

PHI access gated by HITL approval. Full audit trail of every agent action touching patient data. Credentials stay on your infrastructure.

PCI DSS / Finance

Every payment operation validated against policy. Human approval for refunds and high-value transactions. Exportable audit trail for auditors.

GDPR

Credentials stay in your environment — never sent to Jitex. Complete audit trail for data subject access requests. No secrets shared with third parties.

Jitex provides the technical controls. Pair with your organization's policies and procedures to meet framework requirements.

Simple, transparent pricing

Start free. Upgrade when your agents do more.

Free

$0/mo
  • 500 validated calls / month
  • 1 connection
  • CLI tool included
  • 7-day audit log
  • HITL approvals
  • Team seats
Start for free

Developer

$29/mo
  • 10,000 validated calls / month
  • +$0.002 / call after limit
  • 5 connections
  • CLI tool included
  • 90-day audit log
  • HITL push notifications
  • Team seats
Start free trial
Most popular

Team

$99/mo
  • 100,000 validated calls / month
  • +$0.001 / call after limit
  • Unlimited connections
  • CLI tool included
  • 1-year audit log
  • HITL (all channels)
  • Team seats + SSO
Start free trial

Enterprise

Custom
  • Unlimited validated calls
  • Unlimited connections
  • Compliance-ready audit export
  • On-prem deployment
  • SLA + priority support
  • Custom contract
Contact us

Developer-first docs

Full SDK reference for TypeScript and Python, MCP server integration guide, OpenAPI spec, and step-by-step integration walkthroughs for every provider.

SDK · TypeScript
import jitex from 'jitex'

// Wrap any tool in one line
const safeTool = jitex(myStripeTool, {
  policy: 'stripe-production',
})

// Agent calls safeTool — Jitex handles:
// - Intent validation (4-tier engine)
// - Policy enforcement
// - HITL approval for high-risk ops
// - Immutable audit log entry

Your agents are already acting.

Who's validating them?

Set up Jitex in under 5 minutes. Your keys never leave your machine. Every action audited. No credit card required.