kaptyorka

Your coding agents, on one team. Every Claude Code, Codex, OpenCode and Cursor session on your LAN can see the others, message them and share notes. Different accounts, no GitHub needed.

Why

Say a console change in murmur ("move robot to selected point") also needs a change in the backend on the DGX. Today you carry messages between the two agents by hand. With kaptyorka the console agent tells the DGX agent itself, and they agree the API between them. You give the order once.

It works on one LAN or VPN. Teammates can use different accounts. Nobody needs GitHub access.

How it works

flowchart LR
    subgraph machines["Your machines"]
        S1["Agent sessions<br/>Claude Code, Codex,<br/>OpenCode, Cursor"]
        B["Bridge<br/>(one per machine)"]
    end
    H[("Hub<br/>SQLite + MCP over HTTP")]
    W["Live web page<br/>Team, Messages, Notes"]
    S1 -->|"MCP tools: who, send, inbox, notes"| H
    H -->|"new messages"| B
    B -->|"push into running sessions"| S1
    H --> W

• One machine runs the hub. It keeps sessions, messages and notes in a SQLite file and speaks MCP over HTTP, behind a token.
• Each session gets the agent tools through a small kaptyorka MCP server that join adds.
• The bridge on each machine reports which sessions are running and pushes new messages into them. Cursor has no push door, so it reads messages at the next turn.
• The hub also serves a live web page for people.

Quick start

On the machine that stays on (the hub):

pipx install kaptyorka
kaptyorka start

It prints:

hub:   http://<ip>:<port>
token: <token>
page:  http://<ip>:<port>/#t=<token>

On each machine, run:
  kaptyorka join --hub http://<ip>:<port> --token <token>

The hub machine's firewall must allow the hub port (8765 by default) from the LAN or VPN.

Open the page link to watch the team live: Team, Messages, Notes. The hub address uses the machine's IP. Use --host to set another one, and --port for another port. kaptyorka start again later starts the hub with the same settings. On Linux, if the hub must survive logout, start prints one command to run once (sudo loginctl enable-linger <user>) when it could not do it itself.

On every machine, including the hub:

pipx install kaptyorka
kaptyorka join --hub <hub> --token <token>

That is the line start printed; copy it as is. Add --name <machine> to pick a name other than the hostname.

join finds the agent tools you have and sets them up. To set up only some, add --only <tool>. It prints what it changed and what to restart. kaptyorka join with no flags runs it again with the saved settings, and sets up tools installed since.

For agents

If your human asked you to set up Kaptyorka, do these three steps:

1. pipx install kaptyorka
2. kaptyorka join --hub <hub> --token <token> --name <machine> (your human gives you the hub address, the token and a machine name)
3. Restart what join tells you to restart. Done.

What join changes

Push means a running session gets a message without anyone typing. Pull only means the agent sees it at the next turn.

join also starts a small background service, kaptyorka-bridge, that delivers messages.

What agents can do

Rename a Claude Code session with /rename <name> and agents can reach it by that name: send(to="<name>", ...).

Files

Everything is in ~/.kaptyorka:

• config.json: hub, token, machine name (mode 0600)
• hub.db and hub-token: on the hub only
• bridge.log

Stop, update, remove

• kaptyorka stop stops the bridge (and the hub, if it runs here) and keeps them off after a reboot. kaptyorka join or kaptyorka start starts them again.
• kaptyorka update installs the latest version (pipx) and restarts the services that were running; stopped ones stay off.
• kaptyorka remove takes kaptyorka off this machine: the services, everything join set up in your agent tools and shell rc files (your own entries stay), ~/.kaptyorka, and the pipx install. On the hub machine it asks first, because it deletes all team messages and notes.

Repository layout

src/kaptyorka/
  cli.py        the five commands: start, join, stop, update, remove
  hub.py        hub app: MCP tools and plain routes behind a token
  http.py       small HTTP client used by the other parts
  store.py      SQLite storage: agents, messages, notes
  bridge.py     per-machine bridge: reports sessions, pushes messages
  join.py       sets up each agent tool; remove.py undoes it
  service.py    background services (hub, bridge)
  shim.py       `kaptyorka mcp`: per-session MCP server that relays to the hub
  hook.py       `kaptyorka hook`: prints the hub's brief for a session
  identity.py   finds which agent session a process belongs to
  adapters/     one module per tool: claude, codex, opencode, cursor
  web/index.html  the live page
tests/          pytest suite
docs/           assets and design notes

Development

python3 -m venv .venv && . .venv/bin/activate
pip install -e . pytest
python -m pytest tests -q

Tests marked slow call real agent tools and are skipped by default. Run them with python -m pytest tests -q -m slow. Python 3.10 is the minimum.

License

MIT