VELA: Securely execute AI-generated & untrusted code

Hey Product Hunt community!

As a solo creator, I’m diving deeper into the world of autonomous AI agents (Langchain, Laminedex, etc.). One of the biggest hurdles I faced was code execution.

When an agent needs to analyze data, scrape a site, or run a simulation, it writes code. But where do you drive it safely?

  1. exec() or subprocess on host machine? Horrible. One bad prompt injection and LLM accesses your .env files or exfiltrates data.

  2. Standard Docker container? Too slow and heavy for rapid-fire agent tool calls.

  3. Cloud Sandbox? Great, but I didn’t want to send my local data or proprietary agent logic to a 3rd party API just to run a simple pandas script.



<a href

Leave a Comment