Secrets management for AI agents
(Afrikaans: "yeeees... no" — the sound of a gatekeeper with opinions)

Your AI agents are running wild with your API keys.

We fix that.

The Problem

The Solution

  1. Store your API keys in Janee — Stripe, Twilio, exchanges, databases
  2. Agent requests access with intent — "I need Stripe to check balance because user asked"
  3. LLM evaluates the request — Legit? Within policy? Suspicious?
  4. We proxy the call — Agent never sees the real key
  5. Everything logged with reasoning — Full audit trail
# Before (terrifying)
agent_config = {
  "stripe_key": "sk_live_...", # 😱
  "aws_secret": "...", # 💀
}

# After (sane)
janee_token = janee.request_access(
  service="stripe",
  reason="checking balance for revenue query"
)
# Agent gets scoped, audited access ✅
🚧 Status: Pre-MVP. We're building in public. First version ships in the next few weeks.

Get early access