Skip to navigation
SDKs and CLI

Sikaru CLI

Install the Sikaru command-line client, discover and validate requests, pick a model per run, enable automatic improvement, and choose where runs execute.

View as Markdown

The Sikaru CLI is the command-line client for the Sikaru public API. Use it to manage agents and sessions, start runs, inspect events, submit tool results, and work with files and artifacts from scripts or your terminal.

Install

Install the latest release on macOS or Linux:

curl -fsSL https://sikaru.ai/install.sh | sh

Discover and validate requests

Set SIKARU_API_KEY in your environment. Use --base-url to override the API endpoint. Discover operations and request fields with help or machine-readable schemas:

sikaru agents --help
sikaru runs --help
sikaru runs start --help
sikaru runs start --schema
OptionPurpose
--helpShow an operation’s required fields.
--schemaPrint the machine-readable request schema.
--dry-runValidate a request without sending it.
--format jsonStructured output for scripts.

Mutation requests are not automatically retried.

See Local compute to attach a machine you control. Continue with CLI automation for detailed usage.

Select a model for one run

Add --model MODEL_ID, using an ID from your project catalog, to sikaru runs start. This pins the selected model for that run without changing the project default. Omit the flag to use the project default. Unknown model IDs are rejected before run creation. Provider URLs and credentials stay service-managed.

List catalog choices and the current project default with:

sikaru model_settings get_model_settings --project-id "$PROJECT_ID"

Per-run selection requires a service deployment that supports the model request field. Existing execution sessions keep their previously selected model.

See Models and output for catalog discovery, reasoning controls, and structured responses.

Turn on automatic harness improvement

Add --auto-improve when you start a run:

sikaru runs start --project-id PROJECT --harness-id AGENT \
  --tenant-id TENANT --user-id USER --input '{"goal":"Complete the task"}' \
  --product-context '{}' --policy '{}' --auto-improve

Or enable it for the turns of a new session:

sikaru execution-sessions create --project-id PROJECT --harness-id AGENT \
  --tenant-id TENANT --user-id USER --auto-improve
FactDetail
DefaultOff. --auto-improve=false explicitly disables it at startup.
Requiresruns:create, harness:write, and an agent configured for improvement.
When it runsAfter completed turns’ evidence is graded and the configured evaluation cases are ready. Work continues when the CLI exits.
CostImprovement uses additional model and evaluation compute.
ServiceMust support automatic improvement and have its learning worker enabled. This flag does not run an optimizer on your computer.

Only evaluated improvements can become active. Running sessions keep their pinned release; start a new session to use an approved release. A job that requires review pauses further automatic campaigns for that agent. Inspect progress with:

sikaru harnesses list_improvements --project-id PROJECT --harness-id AGENT

Choose the execution environment

FlagWhere the run executes
--execution-environment managed (default)Sikaru chooses the sandbox.
--execution-environment localA connected machine you control.

See Local compute for attaching an executor.

Next steps

CLI automation

Credentials, output formats, and scripting.

Local compute

Attach a machine you control.

Models and output

Pick a model and constrain output shape.