连接洋葱

build your map and first pages; approve nightly upkeep when prompted

co rem init

Install and start

One line installs co and sets it up: your agent identity, an OpenOnion key with starter credit, and the skills and command index that tell Codex and Claude Code about co.

curl -fsSL https://raw.githubusercontent.com/openonion/connectonion/main/install.sh | sh

It uses uv (installing it if needed) to keep co out of your system Python, so you need no Python of your own. Then connect what you use:

co auth google      # Gmail and Google Calendar
co auth microsoft   # Outlook
co commands         # everything else; add --help to any

<details> <summary>With pip instead</summary>

```bash

what it does, what it changes, an example

$ co linear --help $ co linear issues -n 3 3 open issues CON-3 Todo No priority - 2026-10-01 Import your data CON-1 Todo No priority - 2026-10-01 Get familiar with Linear CON-4 Todo No priority - 2026-10-01 Set up your teams Next: co linear issue CON-3 ```

CLI is all you need

An agent's work lives in many places: your inbox, your calendar, a chat thread, a web page behind a login, a file on the NAS, an issue tracker, its own notes, another agent. ConnectOnion strings all of that context together with one command line, co. The agent reads a thread with one command, looks something up with the next, and writes the answer with a third. Every step is a line in its shell, and the output of one is the input of the next.

See the CLI in action

Watch the 43-second film — real runs from co 1.8.10.

<details> <summary><strong>See search, Linear, Slack, Canny and audit examples</strong></summary>

<picture> <source media="(prefers-reduced-motion: reduce) and (max-width: 600px)" srcset="https://www.connectonion.com/aha-search-mobile-poster.png"> <source media="(prefers-reduced-motion: reduce)" srcset="https://www.connectonion.com/aha-search-poster.png"> <source media="(max-width: 600px)" srcset="https://www.connectonion.com/aha-search-mobile.gif"> <img alt="co search ConnectOnion printing an answer with its GitHub and website sources" src="https://www.connectonion.com/aha-search.gif"> </picture>

co search ConnectOnion answers from the web and cites its sources. The default engine uses your own search key, then ConnectOnion credits; --engine ddg is free.

<picture> <source media="(prefers-reduced-motion: reduce) and (max-width: 600px)" srcset="https://www.connectonion.com/demos/linear-mobile-poster.png?v=2"> <source media="(prefers-reduced-motion: reduce)" srcset="https://www.connectonion.com/demos/linear-poster.png?v=2"> <source media="(max-width: 600px)" srcset="https://www.connectonion.com/demos/linear-mobile.gif?v=2"> <img alt="co linear issues listing three open issues, then co linear create previewing a new issue" src="https://www.connectonion.com/demos/linear.gif?v=2"> </picture>

List your Linear issues, then create one. The create shows a preview and changes nothing until --yes.

<picture> <source media="(prefers-reduced-motion: reduce) and (max-width: 600px)" srcset="https://www.connectonion.com/demos/slack-mobile-poster.png?v=2"> <source media="(prefers-reduced-motion: reduce)" srcset="https://www.connectonion.com/demos/slack-poster.png?v=2"> <source media="(max-width: 600px)" srcset="https://www.connectonion.com/demos/slack-mobile.gif?v=2"> <img alt="co slack search finding a message, then co slack thread reading its replies" src="https://www.connectonion.com/demos/slack.gif?v=2"> </picture>

Search Slack, then read the whole thread. Each message carries the id that co slack send --reply-to takes.

<picture> <source media="(prefers-reduced-motion: reduce) and (max-width: 600px)" srcset="https://www.connectonion.com/demos/canny-mobile-poster.png?v=2"> <source media="(prefers-reduced-motion: reduce)" srcset="https://www.connectonion.com/demos/canny-poster.png?v=2"> <source media="(max-width: 600px)" srcset="https://www.connectonion.com/demos/canny-mobile.gif?v=2"> <img alt="co canny posts ranked by votes, then co canny status previewing a move to planned" src="https://www.connectonion.com/demos/canny.gif?v=2"> </picture>

Your most-voted Canny requests, and a status change you preview before voters hear about it.

<picture> <source media="(prefers-reduced-motion: reduce) and (max-width: 600px)" srcset="https://www.connectonion.com/demos/audit-mobile-poster.png?v=2"> <source media="(prefers-reduced-motion: reduce)" srcset="https://www.connectonion.com/demos/audit-poster.png?v=2"> <source media="(max-width: 600px)" srcset="https://www.connectonion.com/demos/audit-mobile.gif?v=2"> <img alt="co audit co linear scoring 13 help pages and reporting fit for an agent harness" src="https://www.connectonion.com/demos/audit.gif?v=2"> </picture>

co audit scores a CLI's help pages the way an agent reads them. CI runs it on every co page, and it works on any other CLI too.

</details>

Why a command line, and not MCP or a plugin per tool

- Every agent already has one. Claude Code, Codex, Cursor and any agent you write can run a shell command. There is no server to start, no client to configure and nothing to install into the agent. - It costs no context until it is used. Tool schemas sit in an agent's prompt whether it needs them or not. A command line is discovered on demand: bare co lists the groups, co gmail --help explains one, and only the page the agent opens enters its context. - The help page is the prompt. Each --help says what the command does, what it changes (Read-only, Sends, Changes, Deletes…) and gives a real example, so there is no separate skill file or schema to keep in step. CI fails any page that loses one of those parts (co audit). - Every answer names the next step. A list ends with how to open the first item, a missing login ends with Next: co auth microsoft, a typo ends with the command you meant. The agent recovers without asking you. - It composes. Commands pipe into each other and into scripts, and the transcript is the same commands you would type, so you can read exactly what the agent did, and run it yourself.

```console