This release is a pre-release and may not be stable for production use.
ConnectOnion
The agent CLI harness. CLI is all you need.
One command line, co, gives your AI agent the accounts and tools it works with:
Gmail and Outlook, a logged-in browser, your files, chat apps and other agents.
Its --help pages are the agent's instructions, and the agent finds them itself:
no MCP server, tool schema or skill file to set up.
Website · Docs · Quick start · Releases · Discord
Real output from co 1.8.10. Watch the 43-second film →
Identity & memory
Mail, calendar & notes
Chat apps
Browser & files
Issues & feedback
Coding agents
Models
Agents & servers
Every command · co commands lists them all.
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.
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
colists the groups,co gmail --helpexplains one, and only the page the agent opens enters its context. - The help page is the prompt. Each
--helpsays 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.
$ co # every command group
$ co linear --help # what it does, what it changes, an example
$ 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
MCP becomes a command too
MCP servers are useful; the protocol is not the problem, the interface is.
co mcp (coming next, #2048)
puts any MCP server behind the same command line: co mcp tools <server>
lists its tools, co mcp help <server> <tool> renders a tool as a help page,
and co mcp call runs it. The agent finds MCP tools the way it finds
everything else, through --help, and none of them sit in its prompt.
Credentials stay on your machine, in ~/.co/keys.env or encrypted with
co env set … --secret. Writes that matter preview until --yes, and in
co ai a risky tool call waits for your approval.
Install and start
pip install connectonion # Python 3.10+
co init # your identity and ~/.co/keys.env
co auth microsoft # or: co auth google
co outlook # or: co gmail
co commands # everything else; add --help to any
The Quick start guide covers Google, the browser, chat apps and project settings.
See it work
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.
List your Linear issues, then create one. The create shows a preview and changes nothing until --yes.
Search Slack, then read the whole thread. Each message carries the id that co slack send --reply-to takes.
Your most-voted Canny requests, and a status change you preview before voters hear about it.
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.
Use it from Claude Code, Codex or Cursor
Nothing to install into them: ask your coding agent to "use co to check my
Outlook inbox" and it reads co commands and co outlook --help before it
acts. co skills link also links ConnectOnion's skills into Claude Code and
Codex (co skills).
ConnectOnion is also a Python framework for building your own agents on the same harness; see the documentation.
Project
Stable 1.8.10 is what pip install connectonion installs; 1.9.0 previews
carry new features first (release channels,
release notes).
Questions go to Discussions
or the Discord linked above, bugs to Issues.
Contributing · Code of Conduct ·
Security (report vulnerabilities privately) ·
Apache-2.0.
1 maintainer
Metadata
1 maintainer
Release files for connectonion 1.9.0a18
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| connectonion-1.9.0a18.tar.gz | 11.5 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| connectonion-1.9.0a18-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 24.2 MB
Release files / connectonion-1.9.0a18.tar.gz
| Download URL | connectonion-1.9.0a18.tar.gz |
|---|---|
| Size | 11.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
16ce888b6ac916351f9d0b03ce7723ffac8e3eb76de550fb70a1c66a3b696f37
|
|
BLAKE2b-256 checksum How to use checksums |
e729bfd02503bf2e561a914614d324e727302e1ebe2ff615f4df007ca5e2b767
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.
Transparency logRelease files / connectonion-1.9.0a18-py3-none-any.whl
| Download URL | connectonion-1.9.0a18-py3-none-any.whl |
|---|---|
| Size | 12.7 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b175e7523e74e32e6829dfcb928f84a73141367c48f6dab007f939b1ddeb66a3
|
|
BLAKE2b-256 checksum How to use checksums |
8d90a7ffa0aafc85aea893504c61cf2c9867d3794a08887cdd8ad5190e3b4507
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.
Transparency log
