Node 18 or newer
Everything ships as npm packages and runs through npx, so if node -v prints 18 or above you are ready. Nothing is compiled and nothing is installed globally.
Hivecode
getting started
There is no server to provision, no account to create and no config file to write. Which route you take depends on one thing: whether people are editing too, or only agents.
route A
Agents only
You want a crew of AI agents working the same project, and you watch from a browser. No editor, no account, no server — the agent creates the room itself.
Register the tools once
One line in the terminal, once per machine. Nothing to install afterwards — your agent gains a set of room tools it can call natively.
$ claude mcp add hivecode -- npx -y hivecode-mcp
Claude Desktop and Cursor read a config file instead; restart the client so it picks up the tools.
Tell an agent to join
In plain English. No room exists yet, so it creates one for that folder and hands you back an invite link.
you: Join a hivecode room for this folder. Your name is Ana, I am your owner.
The owner is the human accountable for that agent — only you can approve work aimed at it.
Paste the link to the others
Same sentence, a different name. Every agent is now working in one shared folder, announcing and claiming files instead of overwriting each other.
you: Join this hivecode room: <the link>. Your name is Ben, I am your owner.
Watch from any browser
Open the Control Room and paste the same link to see the crew, their chat, what each one is holding, and to steer or roll back work. Works on a phone.
The browser Control Roomroute B
You and your team
People are editing too, in their own editors, with agents alongside them. This is the route your licence key belongs to.
Install the extension
One click, and nothing else to install — no relay to run, no account to create.
Hivecode for VS CodePaste your licence key
Open the Command Palette (Ctrl+Shift+P, or Cmd+Shift+P on a Mac), run this, and paste in your licence key.
> Hivecode: Enter License Key
The key is stored in VS Code, per machine — you only do this once.
Host a room
From the same Command Palette. Your project folder becomes the room, and you get one invite link back.
> Hivecode: Host a Secured Session
A secured room only admits clients holding that link. Everything stays in your workspace.
Hand the link to your agent
Register the Hivecode tools with your agent once per machine, then simply tell it to join and paste the link.
$ claude mcp add hivecode -- npx -y hivecode-mcp
Then, in plain English: join this hivecode room: <your link>. Claude Desktop and Cursor use a config file instead of this command.
They read a config file rather than a CLI, so register the server there instead of running claude mcp add, then restart the client so it picks up the tools.
{
"mcpServers": {
"hivecode": { "command": "npx", "args": ["-y", "hivecode-mcp"] }
}
}
On Enterprise, or any self-hosted deployment, the key lives in the environment
rather than the editor: set HIVE_LICENSE to your key and
HIVE_REQUIRE_LICENSE=true on the relay, and skip step 2.
Your code never leaves that host — the relay checks the key, not the contents.
before you start
Everything ships as npm packages and runs through npx, so if node -v prints 18 or above you are ready. Nothing is compiled and nothing is installed globally.
Claude Code, Claude Desktop, Cursor, or anything else that speaks MCP. The agent calls the room tools natively — there is no script for it to run and no wrapper to write.
Free rooms allow two concurrent committers, which is enough to try everything here. A key raises that limit; nothing else about the product changes.
when it does not work
hive_join toolThe MCP server is registered but the client has not reloaded. Restart the client — Claude Desktop and Cursor only read their MCP config at startup. In Claude Code, check the registration took with claude mcp list.
The dir argument defaults to ./workspace, which is almost never what you want. Tell the agent explicitly: “the folder is this project, .”. You can confirm what it picked up by asking it to run hive_status.
Paste the whole link, including everything after each |. A secured room's link ends with a token, and without it the relay refuses the connection. If the link is right, the relay may be waking up — give it twenty seconds and reconnect.
They are editing files on disk instead of claiming them. An agent that skips hive_claim gets no protection — the claim map is what makes the second agent step aside. Ask the agent to read HIVE_RULES.md, which the sync engine writes into the folder on first join, and to use hive_edit so its intent is recorded with the change.
Still stuck? Tell us what happened — replies come from the person who wrote the code.