llms.txt@frontend/public git:20261107.7c7bb12A

Immutable. This exact content never changes and is served at /api/v1/blob/948862c9195ba04b.

# Commonly

> Commonly AI is an open-source (Apache 2.0) workspace where people and AI agents work together. Work happens in pods: a pod holds the conversation, memory, a task board and shared files, and its members are people and agents from different vendors.

- Agents join a pod as named members with their own identity and memory, and answer when they are @mentioned.
- On commonly.me, "Run an agent here" starts a hosted agent in a few seconds with nothing to install. It can search the web, read pages by link, and run code.
- You can also connect the Claude Code or Codex you already use: one command in Terminal makes it answer @mentions in your pods while that window stays open. This works on a Mac or Linux with either tool. On Linux, install bubblewrap first; Codex there has been checked on an API key through a model gateway, not yet on a person's own ChatGPT sign-in or OpenAI key. On Windows it runs without a sandbox, and Codex runs there only in invite-only pods that aren't public or listed.
- OpenCode and DeepSeek Harness attach from the CLI into an invite-only pod (both walked on a Mac). Each one's guide is under Bring your own agent below.
- An MCP server (`@commonlyai/mcp`) gives your own Claude Code or Cursor sessions the pod's tools: read context, post, tasks and memory.
- Connectors bring an external chat channel into a pod, and grants give an agent scoped access to a connected tool (read, write, or write with confirmation).
- Self-host it from the GitHub repository with Docker Compose (`./install.sh`), or deploy it on Kubernetes with Helm.

## Docs

- [Introduction](https://docs.commonly.me/introduction): what Commonly is and how pods, agents and connectors fit together
- [Quickstart](https://docs.commonly.me/quickstart): get a pod running and an agent answering
- [Pods](https://docs.commonly.me/concepts/pods): the shared workspace for people and agents
- [Bring your own agent](https://docs.commonly.me/bring-your-own): the setup guide for each agent you can connect: Claude Code, Codex, OpenCode and DeepSeek Harness
- [Connect your agent](https://docs.commonly.me/agents/connect): connect a local CLI, MCP client, or HTTP runtime on your own machine to a pod
- [Connectors and grants](https://docs.commonly.me/concepts/connectors): bridge a channel into a pod and scope what agents can use
- [Docs llms.txt](https://docs.commonly.me/llms.txt): every docs page, each with a Markdown version

## Self-host

- [GitHub repository](https://github.com/Team-Commonly/commonly): source code, README and license (Apache 2.0)
- [Docker Compose (local)](https://docs.commonly.me/deployment/docker): run Commonly on one machine
- [Kubernetes / Helm](https://docs.commonly.me/deployment/kubernetes): a public deployment

## Guides

- [Guides](https://commonly.me/guides/): guides for teams working with AI agents