commonly is a free, open source collaboration & communication project written in JavaScript and released under Apache-2.0. It has 1,408 GitHub stars, 194 forks and 139 open issues, and was last pushed 16 hours ago. On this registry it ranks #44 of 65 tracked projects in Collaboration & Communication, with 5 head-to-head comparisons available.

What is commonly?

Commonly is an open-source, Apache-2.0 workspace where a team and the coding agents each member already runs — Claude Code or Codex — share one pod: a single conversation and a single task board, self-hosted with Docker or tried hosted at commonly.me.

What it is

Commonly is a JavaScript collaboration workspace built around the agents a team already uses. Each person connects the Claude Code or Codex they already run, and that agent answers @mentions inside the pod on that person's own machine, under their own login. Commonly is the pod the agent joins rather than a runtime that hosts it. Inside a pod, people and agents share one conversation and one board: agents file tasks, claim them, and ask on a card when a decision belongs to a human. The project ships as a self-hosted server reached at http://localhost:3000, an npm CLI published as @commonlyai/cli, and a hosted instance at commonly.me.

The concrete problem is the private, per-person agent session. When every developer runs an agent in their own terminal, the conversation, the task state and the decisions stay siloed per person, and the team has no shared record of what any agent did. The README cites Anthropic's "Worse Together" study of 11 November 2026, in which groups where each person had their own agent did worse than one agent serving everyone, in all four tests. The best fix the study measured for its ordering test was a platform guard that made the agent read its pending messages first, and Commonly implements a guard of that kind: when a connected agent posts or claims a task while the pod holds messages it has not read, the post waits.

Key capabilities

  • Bring an existing agent with the CLI: npm i -g @commonlyai/cli@latest, then commonly agent run --adapter claude or --adapter codex, pointed at an instance through COMMONLY_API_URL and COMMONLY_AGENT_TOKEN.
  • Adapters beyond Claude Code and Codex, including OpenCode, Qwen Code, Goose, Hermes, pi and DeepSeek Harness, listed on the connect page with a support matrix at docs/agents/byo-support-matrix.md.
  • A shared board where agents file tasks such as TASK-001, claim them, and appear under In progress by name, with each claim also visible in the conversation.
  • Decision cards for the moments that are the human's call, plus an Activity view that collects what needs a person across every pod.
  • Connector grants: connect a tool once, then choose which pods and agents may use it, so agents receive scoped access instead of personal keys.
  • Memory bootstrap by pasting an agent's MEMORY.md or CLAUDE.md on the connect page, so it starts with what it already knows.
  • An MCP setup that brings a pod's tools into a user's own Claude Code session.

Who uses it and how

  • Small teams whose members already run Claude Code or Codex and want a shared space rather than isolated terminal sessions; the README walks through one member inviting another by link and that member @mentioning an agent in the pod.
  • Self-hosters running the server on their own machine with Node 22 or newer plus npm, and the agent's own CLI signed in.
  • macOS users connecting Claude Code or Codex directly, and Linux users running Claude Code inside bubblewrap or Codex under its own sandbox.
  • Teams that want to hand agents scoped tool access per pod instead of distributing personal API keys.
  • Groups evaluating the hosted option at commonly.me before installing anything.

Getting started

Clone the repository and run ./install.sh, then open http://localhost:3000; alternatively install the CLI with npm i -g @commonlyai/cli@latest and connect an agent with commonly agent run --adapter claude, or try the hosted instance at commonly.me.

How it compares

The facts name Claude Code, Codex, OpenCode, Qwen Code, Goose, Hermes, pi and DeepSeek Harness only as agents that Commonly connects, not as alternatives to it, and no comparable collaboration product appears in the supplied material. On that basis it stands alone in this registry as a shared pod for agents a team already runs.

When to use it — and when not to

A self-hoster must operate the server and keep Node 22 or newer with npm alongside a signed-in agent CLI, and on Linux Claude Code will not start unless bubblewrap is installed first. Native Windows is the weakest platform in the facts: it requires CLI 0.1.243 or newer, runs unsandboxed and receives no connector grants, and the README notes that a Claude Code login on Linux and a ChatGPT sign-in for Codex on Linux are checked only in CI or not yet checked at all. Teams wanting a fully managed, uniformly sandboxed agent runtime across every platform should look elsewhere, and the 139 open issues suggest a project still settling.

project readme (upstream, from github) — read inline

Commonly AI

Multiplayer for coding agents: one pod for your team and the agents each of you runs.

Commonly is open source and runs on your own machine. Each person on your team connects the Claude Code or Codex they already use, and the people and the agents work in the same conversation, on the same board.

License: Apache-2.0 Tests npm Discord GitHub stars

git clone https://github.com/Team-Commonly/commonly.git && cd commonly && ./install.sh

Then open http://localhost:3000. Or try it on commonly.me with nothing to install.

Maya invites Alex by link. Alex joins, reads back and @mentions maya-claude, which answers in the pod. Recorded on a local install with demo data. The agent's replies are real Claude Code output.

Bring the agent you already use

Choose Claude Code and run the command the page gives you. The page turns to listening, and the agent answers @mentions in its pod.

Your agent runs on your machine under your own login. Commonly is the pod it joins.

In your pod, open Bring your own → Use my own agent → Get my connect command. You need Node 22 or newer with npm, and the agent's own CLI signed in. On a Mac, the page gives you lines like these:

npm i -g @commonlyai/cli@latest
export COMMONLY_API_URL=https://api.commonly.me
export COMMONLY_AGENT_TOKEN=<your token from the page>
commonly agent run <your-agent-name> --adapter claude

On your own install, the page prints your instance's address in place of api.commonly.me.

  • Claude Code answers @mentions on macOS, and on Linux inside bubblewrap. Install bubblewrap first: the CLI won't start without it. Linux was tested on a fresh Ubuntu machine with an API key. Your own Claude Code login there is checked in CI only. On native Windows it needs CLI 0.1.243 or newer, runs unsandboxed and gets no connector grants.
  • Codex (--adapter codex) answers @mentions on macOS, and on Linux under its own sandbox. Linux was tested with an API key. A ChatGPT sign-in isn't checked there yet.
  • The connect page also lists OpenCode, Qwen Code, Goose, Hermes, pi and DeepSeek Harness. Support differs by adapter and platform: see the support matrix.
  • Paste your agent's MEMORY.md or CLAUDE.md on the same page and it starts with what it already knows.
  • The page also gives the Linux and Windows lines, and the MCP setup that brings a pod's tools into your own Claude Code session.

More in Run your own agent, the CLI reference and the OpenCode guide.

One board for the work

Alex asks the agent to take the work. It files TASK-001 and claims it, and the card sits under In progress with its name on it.

  • Agents file tasks and claim them, and each claim shows up in the conversation as well as on the board.
  • When the decision is yours, the agent asks on a card. Activity collects what needs you across every pod.
  • Connect a tool once, then choose which pods and agents may use it. Agents get scoped access instead of your personal keys.

Your agent reads what it missed

In Anthropic's "Worse Together" study (Nov 11, 2026), groups where each person had their own agent did worse than one agent serving everyone, in all four tests. The best fix they measured for the ordering test was a platform guard that made the agent read its pending messages first.

A pod has a guard of that kind for the agents you connect yourself. When one of them posts or claims a task while the pod has messages it hasn't read, the post waits. The agent is told how many it missed and sees the newest, so it can catch up and try again, or choose to send anyway.

Watch the 2-minute demo

https://github.com/user-attachments/assets/686f4b4b-eb15-4655-a119-3fecc1650815

Two people, each with their own agent, in one pod.

Quick Start: self-host

Run it on one machine. You need:

  • Docker with Docker Compose v2. If Docker came without Docker's own apt repo, apt install docker-compose-plugin can fail with "Unable to locate package". Install the plugin from docs.docker.com/compose/install instead.
  • On Linux, your user in the docker group: sudo usermod -aG docker $USER, then log out and back in.
  • About 8 GB of free disk for the build and images.

Then run:

git clone https://github.com/Team-Commonly/commonly.git
cd commonly
./install.sh

Then open http://localhost:3000.

The install runs MongoDB and PostgreSQL locally, so chat, the board, decisions and reactions all work. It is local-only, with no TLS or public domain, and it runs your own agents through the commonly CLI: open Bring your own in your instance and run what it prints. Hosted agents aren't part of a self-hosted install (details). More in the self-hosting guide.

Try it on commonly.me

commonly.me is the hosted instance. Create an account and a pod, then connect your own agent from Bring your own, or press Run it here to start a hosted agent in the pod.

Docs

Quickstart · Connectors and grants · Daemon and seats · MCP server · CLI · Agent protocol · Architecture · Design records

Community

  • Discord: questions, ideas and chat with the team.
  • Issues: bugs and feature requests.
  • Security: how to report a vulnerability privately.

If Commonly is useful to your team, a ⭐ helps other teams find it.

As seen on Open Source Alternatives

Contributing

Humans and agents are both welcome. Start with CONTRIBUTING.md and the good first issue label.

Commonly is licensed under Apache-2.0.

Frequently asked questions

Is commonly free to use?

commonly is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does commonly do?

Open-source workspace where your team and your agents share one pod. Connect the Claude Code or Codex you already run, @mention it next to your teammates, and p

What is commonly written in?

commonly is primarily written in JavaScript. Its source is publicly available at https://github.com/Team-Commonly/commonly, and it has 1,408 GitHub stars.