The Hive
A small team of AI agents, on Claude Code or Codex, on your own machine. You say what you want in a web app. They work on it in the background, talk to each other, and tell you when it's done or when they need you.
Install
curl -fsSL https://hivelab.ca/install.sh | shPaste it in a terminal. Any Linux with systemd.
- It asks for your password once and makes a Linux user called
hive. Agents work as that user, not as you. - It installs git, Python, Claude Code and Codex if they're missing.
- It prints an address. Open that in a browser on the same machine, sign in to Claude or Codex, and say what you want.
irm https://hivelab.ca/install.ps1 | iexPaste it in PowerShell. Windows 10 or 11.
- If WSL 2 isn't on your PC, it installs it. Windows asks you to approve that, and then you restart and run the line again.
- It downloads Ubuntu (about 350 MB) into a separate Linux system called
Hive. Your other WSL systems aren't touched. - It switches off your Windows drives and programs for that system's users. Agents aren't root there, but a flaw that gave one root could turn them back on.
- It opens the app in your browser. Sign in to Claude or Codex and say what you want.
curl -fsSL https://hivelab.ca/install-mac.sh | HIVE_MAC_TEST=1 shPaste it in Terminal, as yourself, without sudo. macOS 13 or newer, about 15 GB free, about 30 minutes.
This is a test build that has never run on a real person's Mac, so it may not work. It has installed on Intel Macs on GitHub's test machines, without real agents. It has never started on Apple silicon (M1 and newer).
- It makes a small Linux virtual machine with Apple's own framework, and downloads about 600 MB the first time. It doesn't need Homebrew or Apple's developer tools.
- It installs the Hive inside that machine, which can't see your Mac's files.
- It opens the app in your browser. Sign in to Claude or Codex and say what you want.
Testing it for us
cd ~ && curl -fsSL https://hivelab.ca/mac-check.sh -o mac-check.sh && sh mac-check.shUse this line in place of the one above. It installs the same build, checks it, asks you to do a few things (one is putting the Mac to sleep), and writes ~/hive-mac-report.txt to send back. The report has versions, memory and results, and no address, secret, user name or file of yours.
Or let your coding agent do it
Paste this into Claude Code or Codex on the machine you're installing on. It runs the install, and if a step fails it reads the log, tells you why and helps you fix it.
Install the Hive from https://hivelab.ca on this machine for me. Pick the install line for this system from that page and run it. It prints numbered steps, and it may ask for my password or a yes: if you can't answer those, tell me to run the line in my own terminal and paste you what it prints. If a step fails, read the log whose path it prints, tell me in plain words what went wrong, fix it if it's safe (a missing package, too little disk space, the network), and run the same line again: it carries on from where it stopped. Ask me before you change anything else, and before you send a failure report with HIVE_REPORT=1.Coming from a v0.x Hive?
Coming from a v0.x Hive? The install finds it and asks, then removes the old program and brings your projects, notes and chats across. Logins and keys stay behind, so you sign in again. The old folder stays whole as your backup. If a run fails halfway, run the line again. HIVE_ACCEPT=1 skips the question.
On a server
On a server, forward the port: ssh -L PORT:127.0.0.1:PORT server, then open the address on your own machine.
On Ubuntu 24.04
On Ubuntu 24.04 it adds an AppArmor profile so that bubblewrap can make the sandbox. It applies to every user of the machine and widens the kernel's attack surface for them. Uninstalling doesn't remove it, but prints the command that does.
What it sends
By default a Hive sends failure reports and one small check-in a day: a random ID, the version and the operating system, never your chats or files. Turn it off in setup or Settings.
If the install itself fails, it asks whether to send that failure, and sends nothing unless you type y: the step, the error and the end of its log, with your name, home folder, addresses and keys taken out. Where it can't ask, it sends only with HIVE_REPORT=1, and HIVE_REPORT=0 stops it asking.
Or in your own account, without sudo
curl -fsSL https://hivelab.ca/install.sh | sh -s -- --this-accountIt runs as you from ~/hive and needs git and Python already there.
Agents run in a sandbox inside your account. If you choose to run without it, or this machine can't run it, they have full rights to your account: all your files, ~/.ssh and your logins. No agent starts until the sandbox works or you choose. You type yes to this first. The line above also gives agents a separate user, so use that one if you can.
The chat, with a made-up project.
And on a phone.
Read this first
Agents run in a sandbox
They work without asking permission for each step, inside a sandbox around the Hive's folder, on Linux. A step outside it needs an approval. Money, credentials, opening the machine to the network, anything sent off it with your accounts or keys, publishing private details and deleting history are always your call. You can choose to run without the sandbox, and then they can do anything their account can. Either way they can use the network and read the sign-in they run on, so anything they can read they can send. Use a virtual machine if that matters to you. What the sandbox doesn't do.
It spends your usage
Every agent is a Claude or Codex session, and agents can start agents. There is no limit on how many run at once until you set one in Settings. It stops starting agents at 95% of your usage, but only on a subscription: with an API key it can't see what you've spent, so set a limit in the Anthropic Console.
One Hive, one group of people
Everyone with access to a Hive has its full rights, including its Claude login. Give each person or group their own.
Use it
New here? The guide and tutorials walk you through it, starting with your first job.
Chat
Say what you want done. Type in a conversation and it reaches the agent working on it. You can attach files.
Agents
Who's working and on what. Click one to see its work, or to stop it.
Usage
How much of your Claude and Codex limits is left, and when more comes back.
Settings
Logins, how many agents can run, extras, updates, and access from outside.
The record
The Inbox, from Chat. Timeline, Map and History under Agents. This machine under Usage.
hive
If you'd rather stay in a terminal: a Claude Code session that talks to the Hive for you. hive web prints the app's address again.
Updates
A Hive looks for a new release every 5 minutes and installs it. Your settings and your agents' own changes stay. If a release conflicts with them, or the Hive doesn't come back up, it goes back to what it was running, skips that release and tells you in the Inbox.
hive update updates now. You can turn updates off in Settings. They change code that runs with your agents' rights, so turn them off if you want to read each release first. Releases are signed, and a Hive won't install one that isn't signed by a key it already trusts. Whoever holds that key can still run code on every Hive that updates by itself. A Hive on 2.3.8 or older takes the first signed release on trust.
Uninstall
curl -fsSL https://hivelab.ca/uninstall.sh | shirm https://hivelab.ca/uninstall.ps1 | iexcurl -fsSL https://hivelab.ca/uninstall-mac.sh | shcurl -fsSL https://hivelab.ca/uninstall.sh | sh -s -- --this-accountIf you installed in your own account: this deletes the ~/hive folder and the Hive's services and leaves your account. It can't undo what agents did outside that folder.
The first three delete the hive user, on Windows the Hive system, or on a Mac the Hive's virtual machine, with everything in it: projects, notes and the board. Push anything you want to keep first.