Quick Start
Runnable first steps with kapi — no install, no setup. These are ad-hoc runs: one command, one file, configured by flags — the right shape for one-off jobs, scripting, and CI. For content you work on repeatedly, you'll graduate to a project — see the end of this page.
Each command below carries a ▸ Run button. Pressing it runs the real
kapi binary in your browser — nothing leaves your machine. The first run
takes a moment to start; after that it's instant.
Pseudo-translate a file
Generate pseudo-translations to test your UI for truncation and layout issues.
Press ▸ Run — it seeds a small messages.json and writes messages-qps.json,
which you can preview in the Files panel:
kapi pseudo-translate messages.json -o messages-qps.jsonThe output is accented text like ▒ Ĥéļļö, Ŵöŕļđ! ▒ that exposes untranslated
strings and layout problems. With no --target-lang, kapi uses the qps
pseudo-locale; pass --target-lang to target a real locale.
Size the content
Estimate translation volume for cost planning:
kapi stats messages.jsonExplore formats, tools, and flows
List every format kapi understands, then the processing tools and composable flows:
kapi formats kapi tools kapi flowsEdit before you run
With editable, the command is placed at the prompt instead of running
automatically — press Enter when you're ready, or tweak it first:
kapi stats messages.json --jsonFor a full interactive terminal, open the CLI Playground.
Beyond the demo
The commands that talk to a model or edit files in place run after you install — each has its own guide:
- Read, check, and edit any file —
kapi inspect,kapi check, and the one write verbkapi apply: Edit content and Check content like tests. - Translate with your AI — one
kapi models setupconfirm connects your Claude subscription, an API key, or a local Ollama model: Translate with your AI. - Keep AI output on-brand — brand profiles, scoring, and rewrite: Brand guide in 10 minutes.
- Drive it from Claude — the Agent Skill and MCP server: Use with Claude.
Next: set up a project
Once you work on the same content more than once, capture the languages,
patterns, and flows in a .kapi project so you stop repeating flags and start
accumulating work: create your first project —
desktop, agent, or CLI — then kapi up brings it up to date — toward its ship
gates (Projects explains the model).