AI Agent & Automation Quickstart
This is the fastest, copy-paste path from nothing to a live ChatterMate agent — designed to be run by an AI agent, a CI pipeline, or anyone scripting their setup. Every command supports--json for machine-readable output.
Use the ChatterMate CLI (
chattermate) for account, agent, workflow, and knowledge setup. It is
installed from the chattermate-cli Python package. This is not the self-host Docker tool
(npm install -g chattermate-deploy) — see Quickstart → Self-host
for that.Set up from your AI coding tool
Paste this into Claude Code, Cursor, Codex or Windsurf. You sign up in your own terminal, so your password never goes through the AI tool; it does the rest.Paste this into your AI tool
Already have an account?
Already have an account?
Use this version instead. The dashboard’s Create step gives you the same text, ready to copy.
Self-hosted?
Self-hosted?
Point the command you run yourself at your server. The CLI saves it for every later command:Use your API’s origin, without
/api/v1. Also add --app-url <your dashboard URL> to
chattermate widget create, so the snippet loads the widget from your own dashboard. Your
dashboard’s copy of the prompt already includes both.Add MCP to Cursor
Install the MCP server, then swap in your own token.
CLI docs
Every command, flag and environment variable.
Prefer the browser?
Sign up in the dashboard instead.
TL;DR
Prerequisites
- Install the CLI with pip (
pip install chattermate-cli, orpipx/uvx) — needs Python 3.10+. Prefer npm?npm install -g chattermate-cliinstalls the identical CLI as a wrapper that runs the Python one viauv/pipx, so you needuvorpipxon your PATH. See the CLI reference for all install options. - Nothing else — the CLI targets the hosted API (
https://api.chattermate.chat) by default. SetCHATTERMATE_API_URL=http://localhost:8000to target a local/self-hosted backend.
Step 1 — Authenticate
Pick one:- Sign up (new org)
- Personal Access Token (headless)
--json to capture the result.Step 2 — Create an agent
--type is one of customer_support, sales, tech_support, general, custom. The --json
output includes the new id — capture it for the next steps.
Step 3 — Add knowledge
From a URL, or upload local PDF file(s):Step 4 — Go live with the widget
Create a widget for the agent from the CLI — it prints the widget id and the embed snippet:Drive it over MCP instead of the shell
Prefer to let your AI agent configure ChatterMate through the Model Context Protocol? The same package ships an MCP server (chattermate-mcp). See the MCP Server guide for
a ready-to-paste client config — it authenticates with the same cmat_ Personal Access Token.
Command reference
CLI reference
Every command, flag, and environment variable.
MCP Server
Let an AI agent configure ChatterMate over MCP.