Run up to 100 coding agents at once, each in its own sandbox
Lizard gives every coding agent its own isolated microVM that boots in about 238 ms. You hand Claude Code or Codex a task per sandbox, and the Pro plan runs up to 100 of them in parallel without the agents touching your laptop or each other.
Source
@LizardBuild on X · 2026-10-17
Written in our own words. Credit to the original author. Link checked 2026-10-21.
What they did
Lizard gives every coding agent its own isolated microVM that boots in about 238 ms. You hand Claude Code or Codex a task per sandbox, and the Pro plan runs up to 100 of them in parallel without the agents touching your laptop or each other.
Result (as claimed)
Each agent works in a throwaway VM, so a bad command cannot damage your own machine.
Tools they used
Cost: Claude Code: from $17/mo; OpenAI Codex: free plan, paid from $8/mo.
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 Claude Code, OpenAI Codex. 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 up to 100 coding agents at once, each in its own sandbox What the original author did: Lizard gives every coding agent its own isolated microVM that boots in about 238 ms. You hand Claude Code or Codex a task per sandbox, and the Pro plan runs up to 100 of them in parallel without the agents touching your laptop or each other. Reported result (as claimed by the author): Each agent works in a throwaway VM, so a bad command cannot damage your own machine. Source: https://x.com/LizardBuild/status/2111492342754537792 Tools they used: Claude Code, OpenAI Codex 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 up to 100 coding agents at once, each in its own sandbox What the original author did: Lizard gives every coding agent its own isolated microVM that boots in about 238 ms. You hand Claude Code or Codex a task per sandbox, and the Pro plan runs up to 100 of them in parallel without the agents touching your laptop or each other. Reported result (as claimed by the author): Each agent works in a throwaway VM, so a bad command cannot damage your own machine. Source: https://x.com/LizardBuild/status/2111492342754537792 Tools they used: Claude Code, OpenAI Codex 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 up to 100 coding agents at once, each in its own sandbox What the original author did: Lizard gives every coding agent its own isolated microVM that boots in about 238 ms. You hand Claude Code or Codex a task per sandbox, and the Pro plan runs up to 100 of them in parallel without the agents touching your laptop or each other. Reported result (as claimed by the author): Each agent works in a throwaway VM, so a bad command cannot damage your own machine. Source: https://x.com/LizardBuild/status/2111492342754537792 Tools they used: Claude Code, OpenAI Codex 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
How to run AI coding agents in a sandbox · How to run multiple coding agents together · How to vibe code an app with Claude Code · How to use Claude Code and Codex together
Related use cases
Coordinate coding agents in one group chat with xMatrix
xMatrix is a group chat for people and coding agents across your own machines and repos. Mention Claude Code, Codex, Cursor Agent or Gemini CLI in a channel and it runs locally in your checkout with your own login, each launch in its own git worktree so parallel agents do not overwrite each other.
Make coding agents ask before they delete, push, deploy or migrate
A developer released production-dev-team, an open-source skill for Claude Code, Codex and Cursor that forces an approval step before destructive actions and never lets the agent call something verified without a recorded check.
Watch what all your coding agents are doing from the Mac menu bar
He built Loom, a native macOS menu-bar monitor showing what Codex, Claude Code and Antigravity sessions are doing right now.
Keep coding agents' progress when they crash with a durable harness
Vercel released durable-harness, which wraps Pi, OpenCode, Codex and Claude Code so a run that is killed mid-task can pick up where it stopped instead of forgetting everything. It works locally, on Vercel or on your own infrastructure.