Run AI coding agents in real, local sandboxes, not Git worktrees
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hey HN, I built SuperHQ, an app that lets you run coding agents in local sandboxes (powered by Shuru).No custom UI wrapping the agents, they run as CLI/TUI like they were designed to. It just provides you the tools most of us (okay, maybe just me?) needed for running multiple coding agents in parallel without worrying about breaking your system or work environment.Each agent runs in its own microVM. You mount your projects in, writes go to a tmpfs overlay so your host is never touched, and you get a unified diff view to accept or discard changes. API keys never enter the sandbox, they are swapped in on the wire by a local proxy. You can also use your ChatGPT subscription directly instead of API keys through a local auth gateway.Supports Pi, Codex and Claude Code.
HN · launched Apr 12, 2026 · 6 upvotes (top 72%) · 2 views
Niche: ai agent execution sandboxes · 137 launches, 6 in the last 7 days ▼ -25% · Explore this niche →
Category and tags
- Horizontal
- Dev tools
- Developer
- AI feature
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 137 launches in ai agent execution sandboxes →
Could you build this?
No Running coding agents in fast, isolated local microVMs on macOS requires low-level hypervisor virtualization (Apple's Hypervisor.framework or Virtualization.framework), complex overlay tmpfs filesystems, and custom networking sandboxes.
What it would actually take: The architecture requires Swift/Rust interfacing directly with Apple's `Virtualization.framework` to spin up lightweight Linux guest microVMs, manage virtiofs/tmpfs COW file sharing with the host, and handle guest-host IPC. The hard parts are seamless file-system synchronization without destroying git tracking, network egress sandboxing, and sub-second VM boot times. This requires deep systems-level OS and hypervisor engineering expertise.
Discussion
3 comments analyzed.
Competitors
Other products that read as similar to this one : 1317 launches clear the similarity bar, closest 8 shown.
Attention rank: #1147 of 1318 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 161 days after the earliest competitor.
- Run coding agents in microVM sandboxes instead of your host machine · hn · 2026-04-23 · 63 upvotes · similarity 0.82
- Superset · hn · 2025-12-01 · 24 upvotes · similarity 0.63
- Superset 2.0 · ph · 2026-05-06 · 414 upvotes · similarity 0.63
- Muxin · ph · 2026-10-20 · 3 upvotes · similarity 0.60
- MonkeysCode Code Agent · ph · 2026-09-14 · 1 upvotes · similarity 0.58
- Superset · hn · 2025-12-23 · 96 upvotes · similarity 0.57
- Sandbox Agent SDK · hn · 2026-01-28 · 41 upvotes · similarity 0.56
- Pi pod · hn · 2026-10-02 · 120 upvotes · similarity 0.56
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.