Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gumloop.com/llms.txt

Use this file to discover all available pages before exploring further.

gumloop is the command line for Gumloop. Sign in once, then drive your agents, sessions, MCP integrations, skills, and artifacts from the terminal. Every command has a --json mode so you can pipe results into scripts, cron jobs, or any other tool you already use.

Install

The CLI is the same package as the Python SDK. Install it however you prefer — for a global, isolated install (recommended) use uv or pipx:
uv tool install gumloop
Verify the install:
gumloop --version
The Gumloop CLI runs on macOS and Linux (including WSL). It is not supported on native Windows because credential storage and the OAuth callback server rely on POSIX-only paths. The Python SDK itself works on Windows — import from gumloop import Gumloop directly.

Linux prerequisites

The CLI stores credentials in your OS keychain. macOS Keychain is always available, but on Linux you need one of:
sudo apt install gnome-keyring libsecret-1-0
sudo apt install kwalletmanager
On a headless box without a keychain, skip gumloop login entirely and pass credentials per invocation via environment variables.

Sign in

gumloop login
Pick OAuth (browser) at the prompt. The CLI opens your browser, you click “Allow” on the Gumloop consent screen, and you’re signed in. Tokens are stored in your OS keychain and the CLI refreshes them for you when they expire. Prefer an API key, or running on a headless box? See Authentication.

Your first command

List the agents you can see:
gumloop agents list
ID                NAME                MODEL                       TEAM            ACTIVE
agent_g6f1a2b3    Sales research      anthropic/claude-sonnet-4   team_4f8c92ab   yes
agent_h7e9c1d4    Support triage      openai/gpt-5                team_4f8c92ab   yes
Grab an ID from that table and start a chat:
gumloop sessions create agent_g6f1a2b3 --input "Summarize this week's pipeline."
That’s it. From here, every command works the same way — gumloop <thing> <action>, with --help on anything to see all the flags.

Commands

CommandWhat it does
gumloop login / logoutManage stored credentials
gumloop agentsList, inspect, create, and update agents
gumloop sessionsCreate, inspect, send messages to, and cancel agent sessions
gumloop mcpExplore connected MCP servers and execute their tools
gumloop skillsList, upload, update, and download skill files
gumloop artifactsList and download artifacts produced by agents

Global flags

These work on every command:
FlagEnv varDescription
--team-idGUMLOOP_TEAM_IDScope the command to a single team (workspace).
--base-urlGUMLOOP_BASE_URLOverride the Gumloop API base URL (useful for self-hosted/staging).
--version, -VPrint the CLI version and exit.
--help, -hShow contextual help for any command or subcommand.
Most subcommands additionally accept --json to print the raw response payload instead of the human-friendly table, which is handy for piping into jq, scripts, or other tools.