Ask HN: What are agent sandboxes missing?

A developer is building an agent sandbox platform with customizable templates using the OpenCode SDK, aiming to improve CLI experience for AI clients like Claude Code and Codex. The platform will include an AI gateway layer for monitoring, secrets distribution, and access control, and the developer is seeking feedback on existing sandbox solutions.

I'm building an agent sandbox platform with opinionated customizable templates for general purpose agents using the OpenCode SDK. The idea is to provide a great CLI experience so it's easy to use an AI client like Claude Code or Codex to launch sandboxes, fetch/retrieve data and prompts, review generated outputs, and manage queues for ask-user questions. I also plan to add an AI gateway layer, similar to Tailscale Aperture not affiliated but one of their engineers gave a great talk at AI Engineer it's on YT for monitoring network access, distributing secrets, and controlling what services/systems a sandbox has access to. For people building agent workflows, I'd love to hear feedback if you've tried other sandbox solutions. What was missing and what was the hard part? Comments URL: https://news.ycombinator.com/item?id=48835097 https://news.ycombinator.com/item?id=48835097 Points: 2 Comments: 0