Run every agent task in its own Firecracker microVM, as Perplexity does
Perplexity open-sourced SPACE, the sandbox behind Perplexity Computer. Every task gets its own Firecracker microVM, so code the model writes runs isolated from everything else.
Source
@stretchcloud on X · 2026-10-15
Written in our own words. Credit to the original author. Link checked 2026-10-21.
What they did
Perplexity open-sourced SPACE, the sandbox behind Perplexity Computer. Every task gets its own Firecracker microVM, so code the model writes runs isolated from everything else.
Result (as claimed)
Open source; a reference design for anyone running untrusted agent code.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Perplexity Computer. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Run every agent task in its own Firecracker microVM, as Perplexity does What the original author did: Perplexity open-sourced SPACE, the sandbox behind Perplexity Computer. Every task gets its own Firecracker microVM, so code the model writes runs isolated from everything else. Reported result (as claimed by the author): Open source; a reference design for anyone running untrusted agent code. Source: https://x.com/stretchcloud/status/2110846174651679186 Tools they used: Perplexity Computer Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Run every agent task in its own Firecracker microVM, as Perplexity does What the original author did: Perplexity open-sourced SPACE, the sandbox behind Perplexity Computer. Every task gets its own Firecracker microVM, so code the model writes runs isolated from everything else. Reported result (as claimed by the author): Open source; a reference design for anyone running untrusted agent code. Source: https://x.com/stretchcloud/status/2110846174651679186 Tools they used: Perplexity Computer Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Run every agent task in its own Firecracker microVM, as Perplexity does What the original author did: Perplexity open-sourced SPACE, the sandbox behind Perplexity Computer. Every task gets its own Firecracker microVM, so code the model writes runs isolated from everything else. Reported result (as claimed by the author): Open source; a reference design for anyone running untrusted agent code. Source: https://x.com/stretchcloud/status/2110846174651679186 Tools they used: Perplexity Computer Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
Related use cases
Get one inbox for every coding agent that needs you
Agentrix is one inbox for AI coding tasks that need your attention, like Claude Code waiting for approval or Codex finishing, so you keep your CLIs and stop hopping between tabs.
Let an agent review and fix every open PR overnight, and watch your usage
A developer let Amp work overnight on his open-source repo with one prompt: review every PR, wait for CI and Codex bot review comments, resolve them, re-request review, run an end-to-end test and prove everything worked. Claude Code hit its usage limit for 5 hours mid-run.
Give every coding agent the same structured delivery workflow
AI-DLC from AWS Labs turns AI coding assistants into a structured, verifiable software delivery workflow. One harness-neutral core runs in Claude Code, Kiro, Codex CLI, Cursor, opencode and GitHub Copilot, installed with one command.
Grafana agent observability for Hermes Agent
Shipped Grafana agent observability for Hermes Agent and shared it as a Show HN.