MoneyX · @EverydayAi10
Test an AI agent on a small investing account
Let an AI agent trade a small Robinhood account isolated from his other accounts.
$12.95/mo to start2-4 hoursBeginner
How to run AI coding agents in a sandbox
Short answer: Run the agent somewhere it can break things safely: a container or devcontainer on your machine, a cloud microVM per task, or a throwaway virtual machine that is deleted afterwards. Builders below give each Claude Code or Codex run its own isolated microVM, turn a spare Mac into disposable macOS desktops for agents, and add local guards that flag exposed secrets and risky commands before they run. Keep real API keys and production credentials out of the sandbox, give the agent only the repo it needs, and review what it wants to push or deploy.
Sandboxes, microVMs, containers and secret guards builders use so a coding agent cannot damage their machine, leak keys or touch production. 24 matching use cases below, each with a public source.
Looking for something else? Search all 1241 use cases or .
Get started in 3 steps
- Start with your agent's built-in sandbox or a devcontainer, and only switch off permission prompts inside an isolated environment.
- Give the sandbox short-lived, low-privilege keys; never mount your home folder, SSH keys or production .env files.
- Add a guard or a pentest pass before shipping: tools below catch leaked secrets and try to prove vulnerabilities in what the agent built.
Dev & opsX · @pinatacloud
Catch leaked secrets and risky agent actions before they run with Doorman
Pinata built Doorman, an open-source guard that runs locally next to Claude Code, Codex or Cursor. It checks what the coding agent is about to do and flags exposed API keys, suspicious instructions planted in files and risky actions before they happen.
$17/mo15 minutesBeginner
Automation & businessX · @RoundtableSpace
Deploy an open-source team agent in Slack with your own models
QM, open-sourced by Y Combinator, gives every employee their own agent with memory, files, permissions and a sandbox, and also works in Slack channels: it searches notes, email and docs, triages inboxes, opens PRs and runs scheduled jobs. You deploy it by telling your coding agent to follow the repo guide.
$17/mo1 dayAdvanced
Dev & opsX · @rsg_rishi
Audit a vibe-coded app for leaked secrets, missing RLS and dead buttons
Vibe Aegis v2.0 is an open-source safeguard and adversarial audit loop that runs in one command across Claude Code, Codex and Cursor. It targets what agents often ship: exposed NEXT_PUBLIC_ secrets, tables without row-level security, IDOR bugs, client-trusted checkout prices, double-spend race conditions and dead placeholder links.
$17/mo15 minutesIntermediate
Dev & opsX · @chasedovey
Call any coding agent harness by name from one sandboxed server
He built an open-source server where you name the harness (Claude Code, Codex, Pi or about 20 more) and send a request, with each run sandboxed. Use it for one-off jobs, build agents on top, or write loops instead of prompts.
$17/mo1 hourAdvanced
Dev & opsX · @JuancaRodicio
Run Claude Code, Codex, OpenCode and Pi in one workflow that ends in a pull request
Aqorin 0.3.0 is a TUI and CLI that gives each role its own runtime and model, sandboxes writes on macOS, lets your own checks decide when work passes, and turns a finished run into a pull request.
$17/mo15 minutesIntermediate
Dev & opsX · @BIGMayrr
Run Claude Code on OpenAI or Gemini models through a proxy
claude-code-proxy is an open-source proxy that translates Claude Code's API requests so it can run on OpenAI or Gemini models. You keep the Claude Code interface and choose the backend, using your own API keys.
$17/mo30 minutesIntermediate
Dev & opsX · @inlovewithgo
Run your coding agents as pixel workers in a browser office
The Agent Office shows Command Code, Claude Code, Codex and five more agents as pixel workers. You hire them into Daytona, Vercel or Railway sandboxes, drive them from the browser and approve actions with one key.
$17/mo10 minutesIntermediate
Dev & opsHacker News · amrrs
Run your own LLM proxy to see exactly what your agents and apps spend
A builder argues the provider dashboards are not real token statistics and routes every agent, harness and app through a self-hosted LLM proxy instead. One endpoint covers many providers and models, logs which key called which model from which client and when, and hands out virtual API keys so the main key is not pasted into every tool.
$17/mo1 hourIntermediate
Dev & opsX · @LizardBuild
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.
$17/mo1 hourIntermediate
Dev & opsX · @sxhivs
Turn a spare Mac into throwaway macOS desktops for your agents
A developer built desktop-plane, an open-source tool that turns a spare Mac into fresh macOS virtual machines agents can use. Each VM starts in about 6 seconds and is deleted after use, and it works with Claude Code, Codex, Hermes or any agent.
$17/mo1 hourAdvanced
Dev & opsHacker News · ErenayDev
Write a Linux driver for an unsupported scanner by letting Claude watch the Windows driver
A GNOME developer wanted to scan his late mother's film negatives on a Plustek scanner that Linux no longer supported. He had Claude Code set up a Windows virtual machine with the scanner passed through, capture the USB traffic of the vendor driver, and compare it with Linux until scans worked. He then had Claude turn the scripts into a reusable hardware reverse-engineering harness.
$17/moA few daysAdvanced
Dev & opsX · @BIGBULLapp
Self-host an agent that builds mini apps from chat and edits its own UI
mobius from mobius-os is a self-hosted personal AI system: you chat with a coding agent through Claude Code or Codex and it builds mini apps on your server and modifies its own UI.
$17/mo1 dayAdvanced
Dev & opsHacker News · caravel
Run your team's coding agents together on shared live boards
Agor is a web workspace where Claude Code, Codex, Gemini and other agents run on isolated git branches with their own dev environments, shown on spatial boards the whole team can watch and build on.
$17/mo30 minutesIntermediate
Dev & opsX · @44errrr
Find the API keys your coding agents saved in their session logs
A developer pointed out that Claude Code, Codex, Gemini CLI, Cursor and Cline save full sessions to disk, including any .env file the agent read, keys pasted in to test a call and printenv output. He warned that these transcripts are a plain-text store of every credential the agent has seen.
$17/mo30 minutesBeginner
Automation & businessHacker News · dimitrismrtzs
Run your company with Claude Code and Codex agents organized into departments
A founder built a self-hosted company OS that he uses to run his business: every agent runs Claude Code or Codex CLI as a persistent sandboxed process with its own workspace, memory, schedules and tools, and teammates collaborate on the agents.
$17/mo1 dayAdvanced
Dev & opsHacker News · celrenheit
Give coding agents a disposable Linux VM instead of your laptop
Built Clawk so coding agents run in a disposable Linux VM rather than directly on your machine.
$17/mo1-2 hoursIntermediate
Dev & opsX · @abhirukprashann
Give each parallel coding agent its own isolated workspace so they stop clashing
While having agents translate C kernel prototypes into Rust and run tests in parallel, a developer kept hitting file locks and agents clashing in one directory. He built Shadow to give each agent an isolated workspace for editing and building.
See pricing pageA few daysAdvanced
AI coding agents
Dev & opsX · @0xrux
Pentest your vibe-coded app with Strix before attackers do
Strix is an open-source AI pentesting tool. Instead of only scanning code, it actively tests your running app for issues like SQL injection and XSS and tries to prove each one is exploitable.
$17/mo1 hourIntermediate
Dev & opsX · @stretchcloud
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.
See pricing page1 dayAdvanced
Perplexity Computer
Dev & opsHacker News · NickySlicks
Run a local AI pentesting agent on a smartphone
Built Nightcrawler, a local AI pentesting agent that runs on a smartphone.
See pricing page1 dayAdvanced
Dev & opsHacker News · vishnukool
Run AI agents in low-cost sandboxes under a dollar a month
YC F26 team built Agent37 sandboxes for running agents at a reported average of $0.37 per sandbox per month.
See pricing page1 hourIntermediate
Dev & opsHacker News · cagster
Self-host a sandbox for code your agent writes
Built Plimsoll, a self-hosted sandbox service for untrusted agent-authored code with isolation reporting.
See pricing page1 dayAdvanced
Dev & opsHacker News · edverma2
Run the pi coding agent in sandboxes on your own server
Built pi pod to run pi coding-agent sessions in isolated pods on a server you control, with composable environments.
See pricing page1 dayAdvanced
Common questions
- How do you run AI coding agents in a sandbox?
- Run the agent somewhere it can break things safely: a container or devcontainer on your machine, a cloud microVM per task, or a throwaway virtual machine that is deleted afterwards. Builders below give each Claude Code or Codex run its own isolated microVM, turn a spare Mac into disposable macOS desktops for agents, and add local guards that flag exposed secrets and risky commands before they run. Keep real API keys and production credentials out of the sandbox, give the agent only the repo it needs, and review what it wants to push or deploy.
- Which AI tools do people use to run AI coding agents in a sandbox?
- Across the 24 sourced use cases in this guide, the most used tools are Claude Code, OpenAI Codex, Cursor, Docker, Gemini.
- How much does it cost to get started?
- 0 of the 24 use cases can start on a free plan. The most common paid starting price is $17/mo (17 use cases). Prices come from each tool's official pricing page.
- How long does setup take?
- 13 of the 24 use cases list a setup time of an hour or less. Each card shows the setup time the builder reported.
- Are these real examples?
- Yes. Every use case links to its public source (an X post, a Hacker News thread or a GitHub repo) with the author and date, so you can check it yourself.
More how-to guides
How to make faceless YouTube videos with AI · How to automate work with n8n and AI · How to vibe code an app with Claude Code · How to build AI agents for SEO and ads · How to run multiple coding agents together · How to build an MCP server for AI agents · How to add memory to coding agents · How to secure vibe-coded apps and agents · How to observe and debug AI agents · How to build agent memory and context layers · How to control coding agents from your phone · How to add payments to vibe-coded apps · How to run local LLMs with AI agents · How to set up Grok Bot agents for real work · How to build with Gemini 4 Argon and Gemini agents · How to use AI agents for taxes, bills and budgets · How to make AI video ads and Reels with agents · How to set up Hermes Agent workflows · How to vibe code a game with AI · How to replace SaaS subscriptions with vibe-coded tools · How to use AI agents for errands, calls and shopping · How to use Cursor agents and automations · How to make 3D scenes and models with AI and Blender · How to use Claude Code skills and plugins · How to cut AI coding agent costs and token use · How to automate a small business with AI agents · How to compare AI models on the same prompt · How to build hardware projects with AI agents · How to make AI music videos and songs · How to use AI agents with Obsidian and your notes · How to build apps and games for your kids with AI · How to use ChatGPT for real projects and everyday tasks · How to make AI agents ask for approval before they act · How to build AI trading and investing agents · How to build AI agents that make and answer phone calls · How to plan meals and groceries with AI agents · How to use AI agents for fitness and health · How to undo, checkpoint and stop runaway coding agents · How to use AI agents for job hunting · How to automate social media posts with AI agents · How to build a smart home and voice assistant with AI agents · How to make money with AI agents · How to build a website with AI agents · How to use AI agents for research and science · How to build an iPhone or Android app with AI · How to automate email and your inbox with AI agents · How to use AI agents for Linux, servers and homelabs · How to build Telegram, Discord and WhatsApp bots with AI · How to research memecoins and crypto with AI agents · How to remove ads and bloatware from your smart TV with AI · How to self-host AI agents on a Raspberry Pi, Mac mini or homelab · How to learn anything with an AI tutor · How to build an AI second brain and personal wiki · How to reverse-engineer and revive old devices with AI · How to edit videos with Claude Code and Codex · How to set up an AI family assistant · How to make a Godot, Unity or 3D game with AI agents · How to build a custom Android TV or Google TV launcher with AI · How to use Claude Code and Codex together · How to build your own invoicing and bookkeeping app with AI · How to make a browser arcade game with AI · How to make a product demo or launch video with AI · How to fix Wi-Fi and secure your home network with AI · How to control Claude Code and Codex by voice · How to design a PCB and electronics with AI · How to save, share and resume coding agent sessions · How to make a multiplayer game with AI · How to let AI control your computer (computer use)