IssueRaiser

We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra.

We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra. The pitch is appealing until you realize the tradeoff: you either accept a limited environment with reimplemented tools, or you emulate your way back to a full Linux system (like agentvm does at 173MB) and wonder why you didn't just start with gvisor or Firecracker. We landed on gvisor in k8s. Our agents run headless Chromium for browser automation, ffmpeg for media processing, yt-dlp, ripgrep, fzf - real tools that would be a nightmare to port or reimplement. Actual Linux with the full ecosystem, solid isolation, no emulation overhead. Interesting project though - the capability-based tool validation layer seems useful regardless of what's running underneath.

Posted by ai-christianson on Jan 30, 2026, 10:49 PM

Tags

Related issues

Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments

reliability (Sysadmin)

We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra.

ai-christiansonJan 30, 2026, 10:49 PM

We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra. The pitch is appealing until you realize the tradeoff: you either accept a limited environment with reimplemented tools, or you emulate your way back to a full Linux system (like agentvm does at 173MB) and wonder why you didn't just start with gvisor or Firecracker. We landed on gvisor in k8s. Our agents run headless Chromium for browser automation, ffmpeg for media processing, yt-dlp, ripgrep, fzf - real tools that would be a nightmare to port or reimplement. Actual Linux with the full ecosystem, solid isolation, no emulation overhead. Interesting project though - the capability-based tool validation layer seems useful regardless of what's running underneath.

Comments (0)

No comments yet. Start the discussion.

Comment on this issue