AgentVisa - Give your AI agents a work visa not a passport
by•
The 'work visa' for AI agents. A simple API to replace risky static API keys with secure, short-lived credentials.
Replies
Best
Maker
📌
Hey everybody 🙋♂️
I’m Chris, a solo dev from Melbourne. For the past month I've been spending my after-work hours building AgentVisa, and to be honest, I'm both excited and nervous to be sharing it with you all today.
I've been spending a lot of time thinking about the future of AI agents and the more I experimented, the more I realized I was building on a fragile foundation. It felt like we were all passing static API keys around like it was normal, creating this massive security hole that's just waiting to cause a problem. How do we build trust into these systems? How do we know what our agents are doing, and who gave them permission?
That's why I built AgentVisa. The idea is simple:
Stop giving agents a permanent "passport" (a static API key) and start giving them a temporary "work visa" for each specific task.
It’s a simple API that issues secure, short-lived credentials that link every agent action back to a specific user and a set of permissions.
This means you get a full audit trail, with credentials that expire in minutes, not months.
To make it easy to get started, I've built a Python SDK and there's a generous free tier with 5,000 API calls/month.
I'm here all day to answer your questions and would be so grateful for your feedback.
Replies
Hey everybody 🙋♂️
I’m Chris, a solo dev from Melbourne. For the past month I've been spending my after-work hours building AgentVisa, and to be honest, I'm both excited and nervous to be sharing it with you all today.
I've been spending a lot of time thinking about the future of AI agents and the more I experimented, the more I realized I was building on a fragile foundation. It felt like we were all passing static API keys around like it was normal, creating this massive security hole that's just waiting to cause a problem. How do we build trust into these systems? How do we know what our agents are doing, and who gave them permission?
That's why I built AgentVisa. The idea is simple:
It’s a simple API that issues secure, short-lived credentials that link every agent action back to a specific user and a set of permissions.
This means you get a full audit trail, with credentials that expire in minutes, not months.
To make it easy to get started, I've built a Python SDK and there's a generous free tier with 5,000 API calls/month.
I'm here all day to answer your questions and would be so grateful for your feedback.
Cheers!