kapi run

$ kapi run [flow-name] [flags]

Run a composed flow that chains multiple tools together.

Flows are multi-tool pipelines. For single-tool operations, use the tool directly (e.g. "kapi translate" instead of "kapi run translate"). To bring the whole project up to date, use 'kapi up' — the kapi loop lives there; run is the escape hatch for one named pipeline, one pass.

Built-in flows: translate-qa Translate + quality check using AI/LLM

Custom flows can be defined in the kapi.yaml recipe or .kapi/flows/ as YAML files.

Use -p to run a flow from a kapi.yaml recipe: kapi run translate -p kapi.yaml

Commandrun

Groupadvanced

Try it

Runs in your browser against a small sample file. Edit the command before running, or press Run to execute it as shown.

$ kapi run translate-qa -i app.xliff --target-lang fr

Flags

Flag	Type	Default	Description
--api-key	string		API key for the AI provider
--batching	string		how many blocks share one LLM call: auto (default), single
--concurrency, -j	int	0	number of files to process at once (0 = auto)
--context	string		what the model is told about a block besides the block: none, key (default), neighbours
--credential	string		saved credential name to use (see 'kapi credentials list')
--encoding, -e	string	UTF-8	input file encoding
--explain	bool	false	print the resolved source → sink bindings and exit without running
--format, -f	string		override input format detection
--input, -i	stringSlice		input file path(s); repeat for multiple files
--instruction	string		extra guidance for the model while translating (e.g. "informal register; keep product names in English")
--memory	string		named Memory for recycle flow (resolves from KAPI_HOME)
--model	string		AI model name
--output, -o	string		output path or template (e.g. ./out/{name}_{lang}.{ext})
--pack	bool	false	when transforming a .kpz, also eject the result to the .kpz (auto-pack)
--parallel-blocks	int	0	fan out block processing across N goroutines (0 = off)
--progress	string		stream progress events to stderr as NDJSON (value: jsonl); events use the flow-run event vocabulary
--project, -p	string		path to a kapi.yaml project recipe or its directory (auto-discovered from cwd if omitted)
--provider	string	anthropic	AI provider (anthropic, openai, ollama)
--source-lang	string	en	source language (e.g. en, en-US)
--stats	bool	false	include part/block counts in output
--target-lang	string		target language (e.g. fr, de-DE)
--termstore	string		named terms store for term-lookup/enforce (resolves from KAPI_HOME)
--trace	string		write flow trace JSON to file (for flow visualization)

More examples

$ kapi run translate-qa -i messages.json --target-lang de

$ kapi run pseudo -p kapi.yaml # a project-defined flow

← Back to the Command Reference