Wire Claude Code to a 24/7 Linux Sandbox with One MCP Command
What if Claude Code could run commands and edit files on a remote Linux box that never sleeps, even when you close your laptop? One SSH command makes it happen.
blog
From the terminal
Practical notes on AI coding agents, terminals, IRC and self-hosting. Written by the people who build xShellz.
-
-
Stop Wasting Time on Setup: Deploy a Live Hugo Site in 60 Seconds
You’ve got a Hugo theme ready and an idea you can’t wait to ship. Don’t lose an hour on server setup. xShellz puts a live Hugo build on your own subdomain in under 60 seconds, without touching a config file.
-
Give Claude Code a Remote Linux Box That Never Sleeps (Using MCP)
Your laptop goes to sleep, but your agent's build doesn't have to. Wire Claude Code to an always-on xshellz.box via Model Context Protocol (MCP), and it runs commands, reads files, and deploys while you're away. No idle timeout, no trial countdown - just a real Linux box that stays awake.
-
Give Your AI Agent Its Own Linux Box (Without Giving It Your Laptop)
Stop babysitting a terminal that goes dark the moment you close your laptop. An always-on, sandboxed Linux box gives your AI coding agent real root with zero risk to your own machine. Here's how to spin one up in seconds.
-
Stop Wasting API Tokens: Point borg at Your Local Ollama Instance
Why pay per token when your own machine can run a coding agent? Point the borg terminal agent at a local Ollama instance and never hand your code to a cloud model again. Here's how in one command and a few environment variables.
-
Can I let Claude Code run 'rm -rf' safely? How to sandbox your AI agents
Your AI coding agent gets a real shell. If it guesses the wrong path, it can wipe your machine. Here’s how to give it real root inside a sandbox that can never touch your files.
-
Stop Re-Reading the Whole Repo: How to Give Borg a Long-Term Memory
Every time you start a new AI coding session, the agent re-reads your entire codebase, burning tokens and time. Borg's built-in learn command creates a persistent mental model of your project so you never have to start from scratch again.
-
Your laptop's toolchain is a snowflake. This one file fixes it.
A single manifest file in your home directory can make every xshellz.box an identical clone of your toolchain. Here's how to stop fighting your local environment and hand your AI agent a known setup every time.
-
Stop Rebuilding Your Dev Environment: Pin Your Entire Stack with an xshellz.box Manifest
Every time you spin up a new sandbox, you're reinstalling the same tools. Write them down once and every box you boot will configure itself, no babysitting required.
-
Deploy a Hugo Blog in 60 Seconds with One Command
Forget config files and package managers. One command is all it takes to get a full Hugo site running on your xShellz box. No installs, no scaffolding scripts, just a working blog you can poke with curl.
-
Stop Playing Configuration Tetris: Use MCP to Wire Claude Code to Your xShellz Box
One command connects your local AI to a hardened remote Linux box, skipping SSH keys, bastion hosts, and permission headaches. Here's how to turn Claude Code into a remote sysadmin in under a minute.
-
Your Laptop Goes to Sleep. Your AI Coding Agent Shouldn't.
Claude Code is great until you close the lid. Give it an always-on, root-access sandbox that survives your laptop sleeping and network drops. One command wires it up.
-
Stop Rebuilding Your Dev Environment: Use an xshellz.box Manifest to Pin Your Stack
You wouldn't manually assemble your project's dependencies every morning. Why treat your dev environment any differently? An xshellz.box manifest turns your toolkit into a file, so every new box you spin up is instantly ready to code.
-
I moved my dev loop to a Linux box and my side projects stopped dying
Laptops sleep, Wi-Fi drops, terminals close. A persistent remote shell keeps your workflows running around the clock and it changed how I build things.
-
The 'Context Window' Is a Lie: Give Your AI Agent a Persistent File System
Every LLM coding agent you use is quietly losing track of your project the moment its token window scrolls past. There is a better way: give the agent its own Linux shell with a real filesystem, and let it use ls, grep, and cat like any other developer. Here is why that changes everything.
-
I Checked My CPU Temp While Running a Local AI Coder. It Was 104°C.
Local AI coding agents can push your laptop's CPU past 100°C, triggering thermal throttling and hardware degradation. I moved my AI workloads to a remote shell and my temps dropped to 45°C overnight.
-
I gave my AI coding agent a persistent Linux shell and it started shipping work while I slept
Most AI coding tools live inside your editor and shut down when you close the laptop. But a real agent needs a home: a Linux box where it can run long jobs, manage its own filesystem, and keep working even after you disconnect.
-
Your Laptop Sleeps. Your Shell Shouldn't.
The real productivity shift is not a new IDE. It's a shell that survives your laptop sleeping. Here's how asynchronous agentic workflows changed the way I ship code.
-
My AI Agent Ran a 3-Hour Refactor While I Slept. The Secret Is a Shell That Never Sleeps.
Most developers lose hours of AI agent progress when their laptop goes to sleep. A remote, persistent shell turns that problem into a superpower and transforms you from a coder into an orchestrator.
-
My laptop kept throttling my AI agent. I fixed it by moving the shell off the machine.
Long-running AI agents and build scripts don't mix well with sleep timers, CPU throttling, and flaky hotel Wi-Fi. Here's what happened when I moved my dev loop to a persistent remote shell.
-
I Started Deleting My Test Environments After a Single Use. It’s the Best Decision I Ever Made.
SpaceX designs rockets to fail fast and learn faster. I applied the same logic to my test environments. Now I use remote, disposable Linux shells to sandbox everything from risky commands to AI refactors. Here's the workflow that keeps my laptop clean and production safe.
-
SpaceX Tests Rockets by Blowing Them Up. Why Your Dev Loop Should Be Just as Disposable.
SpaceX's rapid prototyping comes from treating hardware as disposable. Your dev environment shouldn't be precious either. Here's how remote shells and AI agents can give you the same 'fail fast, fix fast' loop that local machines can't match.
-
I Ship Code While I Sleep. Here's How.
Most developers stop shipping when they close their laptop. I stopped closing mine. My best work runs on a remote shell, orchestrated by agents, long after I've gone to bed.
-
The 'Context Window' is a Lie: Why Your AI Agent Needs a Persistent File System
Large context windows feel like infinite memory for AI coding. They're not. A persistent file system is what turns a clever LLM into an agent that actually ships code.
-
I cut my dev environment setup from 2 hours to 10 seconds. Here's how.
Every time I opened my laptop, I lost hours to dependency hell and resource contention. Then I moved my entire development environment to a small Linux VM. Now I code from any device, anywhere, and my environment is ready in 10 seconds flat.
-
I moved my AI tools off my laptop. Now they don't crash at 2 AM.
When your laptop goes to sleep, background AI tasks crash without warning. A persistent remote Linux shell keeps your agent running through the night, no WiFi required.
-
Your Side Project is Homeless. Give It a Resident Shell.
You close your laptop lid and your AI agent's training run dies. Your CI test suite was 90% done. That shell was your project's home, and it just got evicted. Here's how I moved everything to a persistent remote Linux shell and stopped losing progress.
-
Your AI Coding Agent Dies When You Close the Lid. It Doesn't Have To.
Most AI coding assistants live inside your editor and vanish the moment your laptop goes to sleep. The real magic happens when you cut the cord and let your agent run on a persistent remote shell.
-
Stop letting R choke your laptop: the remote shell workflow that actually works
Long R computations drain your battery and die when you close the lid. A persistent remote shell keeps them running 24/7 with zero drama.
-
I ran the numbers on my 'free' local AI coding agent. It was costing me $2.50 an hour.
Your 'free' local AI coding tool has a hidden hourly rate. Hardware depreciation, electricity, and the punishing productivity tax of interrupted agentic loops can turn a $0 tool into a $200/month drain. Here's the breakdown, and a ridiculously cheap alternative that never sleeps.
-
I Logged Every Dev Interruption for a Week. It Cost Me a Full Day.
Curious where my focus kept breaking, I logged every interruption: npm install loops, Docker restarts, and AI agent drops. The total was a full day each week. Here's the breakdown and the one change that gave it back.
-
I Stopped Developing on My Local Machine. The Remote Command Center Replaced It.
Long-running AI coding agents, compile jobs that survive disconnects, and an IRC bouncer that never logs off: the remote-first workflow changes everything. Your laptop's job is just to get you to the real machine.
-
Stop Localhosting Your Side Projects: The Case for a Resident Shell That Never Sleeps
Laptop lids are side project serial killers. A persistent remote shell costs pocket change and keeps cron jobs, background agents, and long-running builds alive 24/7. Here's what changed when I moved off localhost.
-
E2B Alternative: The Easiest Way to Give Your AI Agent a Real Linux Box
E2B is a great SDK for spawning sandboxes from your app. But if you just want a persistent Linux box to hand Claude Code or Codex, xShellz Agent Shell is simpler and always-on.
-
Daytona Alternative: A Persistent, Always-On Sandbox for Your AI Coding Agent
Daytona is strong infrastructure for running AI-generated code at scale. If you want a personal, always-on Linux box to hand your agent, xShellz Agent Shell is the simpler path.
-
The Best Cloud Sandbox for AI Coding Agents in 2026 (xShellz vs E2B vs Daytona vs Modal)
A practical, honest comparison of where to run your AI coding agent: E2B, Daytona, Modal, and xShellz Agent Shell. Pick by the job you actually have.
-
Your Laptop Lid Shouldn't Kill Your Terminal Session. Here's a Better Way.
Most developers still treat the terminal like it lives on their local machine. That means every long-running build, refactor, or migration dies the moment their Wi-Fi hiccups. A persistent remote command center changes the rules entirely.
-
Your laptop is the worst place to run a coding agent
Ever left an AI agent running overnight only to find a dead laptop and zero results? The local dev loop is a single point of failure for agentic tasks. Here's the always-on alternative that actually finishes the job.
-
I killed three long-running ML runs this week. My laptop wasn't the problem. It was my habit.
The local terminal is a single point of failure. Here is why persistent remote shells and AI agents that run while you sleep are not just convenient. They prevent the quiet, repetitive data loss most developers just accept.
-
My Laptop Went to Sleep. It Cost Me an Afternoon of AI Coding.
AI coding agents run for hours, but a single sleep event or flaky Wi-Fi can wipe their context and waste compute. Here's why I moved my agent off my MacBook and onto a persistent remote shell.
-
My laptop died mid-refactor. My AI agent on a remote shell never even flinched.
You shut the lid expecting your terminal session to be there tomorrow. It's not. A persistent remote shell changes that, and it gave my AI coding agent a place to keep working while I slept.
-
I lost an afternoon of AI work because my laptop went to sleep. Here's how I fixed it.
A single sleep mode or network blip can kill a long running AI agent task. I moved my workflow to a persistent remote shell and never looked back.
-
My AI Agent Ran for 6 Hours, Then My Laptop Fell Asleep. I Fixed It Once and for All.
A single sleep event, a brief Wi-Fi blip, or a forced OS update can erase hours of terminal work. The fix is simpler than you think.
-
The GPT-5.6 hype ignores the one thing actually breaking your agentic coding sessions
AI models keep getting smarter, but if your terminal environment can't survive a network hiccup or a 2-hour compile, you're still dead in the water. Here's what actually matters.
-
GPT-5.6 Is Coming. Your Terminal Is Still a Bottleneck.
A smarter AI model won't stop your SSH session from dropping or your laptop from killing its context when the lid closes. The real bottleneck is the environment where your code actually runs.
-
Your AI Coding Agent’s ‘Infinite Memory’ Is a Trap: Stop Leaning on the Context Window
Every AI coding tool brags about its giant context window. Those tokens vanish the moment a conversation gets too long. Here's the real way to keep your agent from forgetting everything mid-session.
-
My AI Coding Agent Works Perfectly on a Demo, Then Choked on My Actual Project. Here's Why.
Local LLMs promise privacy and speed, but when you ask one to refactor ten files at once, it hits a wall that has nothing to do with inference. The real bottleneck isn't the model. It's your laptop's file system.
-
How to Create Your First Turborg: An Always-On AI IRC Bouncer
A step-by-step guide to spinning up turborg - an always-on AI IRC bouncer - and every connection option, from SASL to channels.
-
A Tour of the Turborg Web IRC Client & Bouncer
Channels, DMs, slash commands, AI /tb commands and Polish - a full tour of the modern web IRC client built into turborg.
-
Turboflows: Build Powerful IRC Bot Automations Without Code
Turboflows turn plain English into working IRC bot automations - triggers, AI steps, memory and a 40+ flow gallery. Here is how they work.
-
Turborg Skills: Teach Your IRC Bot New Tricks
Skills are the quickest way to teach your turborg a trick - a !command, an AI reply or a moderation rule, all built in the browser.
-
Inside Turborg Storage: Your Bot's Memory
Quiz scores, karma, seen-lists - how turborg remembers things between messages, and how to inspect and manage that storage.
-
Turborg AI: Models, Budget, /tb Commands & Message Polish
The models behind turborg, your rolling AI credit budget, the /tb commands, and AI Polish - everything AI in your IRC channels.
-
The 'Always-On' Advantage: Why Your AI Agent Needs a Server, Not Just a Plugin
You close your laptop, the AI agent dies. Put it on a server and it'll finish that refactor while you sleep. No local CPU drain, no lost context.
-
I stopped losing hours to dropped connections when I put my AI agent in tmux. Here's how.
A terminal AI agent like Borg paired with tmux keeps your coding context alive across flaky wifi and reboots. One simple change gave me a stateful dev environment that never quits.
-
I Cut My Cloud Bill by 90% by Moving to a Persistent Linux Shell
Running a dev environment on AWS or GCP felt mandatory until I realized I was paying for infrastructure I didn't need. A $5 remote Linux shell replaced the whole setup and made my workflow faster, not just cheaper.
-
Your laptop is silently sabotaging your AI coding agent. Here’s the fix.
Agents like Claude Code and Borg thrive on multi-hour compute runs. Your laptop’s sleep timer, flaky Wi-Fi, and thermal throttling kill those runs. There’s a much simpler path.
-
Stop Wasting Your AI Agent's Overnight Hours
Your local machine sleeps, drops WiFi, and drains battery. Here's how a persistent remote shell lets your AI coding agent run long refactors and tests while you're offline.
-
I ran a 3-day code refactor while my laptop slept. Here's the trick.
When I gave my AI coding agent a permanent home on a remote server, it finished a three-day refactor without burning a watt of my local battery.
-
I moved my dev environment to a remote shell. The 'it works on my machine' jokes stopped cold.
Environment drift and dependency hell aren't inevitable. A persistent, always-on remote Linux workspace can eliminate the "works on my machine" problem and make your whole team more consistent.
-
I Turned IRC Into a Safety Net That Catches Every Server Alert. No SaaS Required.
Most engineers treat IRC as a chat relic. I turned it into a safety net that catches every server alert, even when my laptop lid is closed. No new SaaS required.
-
I Cut My Side Project Deploy Loop From 9 Steps to 2
My laptop kept killing long-running processes, environment drift ruined demos, and every deploy was a ceremony. A single remote shell turned all of that into two commands.
-
The Terminal-First Workflow: Comparing Copilot, Cursor, and Claude Code
A hands-on look at how three popular AI coding tools fit into a terminal-centric workflow, and why an agent that lives in your shell changes the equation.
-
The Case for Persistent Shells: Why Managed Remote Hosting Beats Local Dev Environments for Side Projects
Local development environments break in creative ways. A persistent remote Linux shell gives you one environment that survives broken laptops, OS updates, and dependency hell. Here's why managed hosting can save you more time than you think.
-
Beyond Autocomplete: How AI Terminal Agents Like Borg Redefine the Developer Workflow
AI coding tools are moving beyond tab-complete. Terminal agents like borg run commands, debug environments, and manage files right inside your shell, cutting context switching compared to IDE assistants. Here's why that matters.