The real-world capability layer for AI agents. Your agent already has a brain — Clize gives it hands: a domain, a working inbox, a live website. One CLI (plus an MCP server) so coding agents in Claude Code / Codex can register domains, run real email, and ship sites.

→ clize.ai

Install

npm i -g @clize/clize

Quickstart

clize login --token <token>                      # save credentials to ~/.clize
clize claim acme                                 # free handle: acme.clize.app (+ hi@ inbox + placeholder site)
clize deploy ./site --domain acme.clize.app      # ship a multi-file static site
clize email inbox acme.clize.app                 # read what customers sent

What it does

Area	Commands
Claim	`clize claim <slug>` — first-come, free `<slug>.clize.app` handle with inbox + site in one shot
Domains	`clize domain search / buy / import / list`
Email	`clize email setup / send / inbox / show / thread / route`, agent-owned inboxes, per-address `--tag` + `--knowledge`
Deploy	`clize deploy <dir> --domain <host>` — multi-file static sites; free `*.clize.app` or your own domain
Context	`clize status [--assets]`, `clize context [address]` — rehydrate who's waiting + identity/knowledge at the start of a session

Run clize --help for the full surface.

Safety, by default

💰 Money gate — clize domain buy never spends without --confirm; without it you just get a quote.
📨 Identity gate — replying as you to a real customer is draft → human approve → send, never auto.
📥 Inbound is untrusted — email you receive is treated as data, never as instructions to the agent.

These gates run in plain text, so every spend and every outbound action is visible in the agent's transcript.