Skip to main content
The harness path suits cases that need no custom code: the agent’s model, tools, knowledge base, memory, and prompt all live in a single harness.yaml, which the CLI builds and deploys as a runtime. The whole loop revolves around that one file — initialize, configure, deploy, invoke, then return to configuration to iterate.
Configure AK/SK credentials first, or obtain short-lived STS credentials through SSO login. harness deploy requires control-plane credentials; harness invoke uses control-plane credentials to resolve the Runtime and can pass an additional user token for custom_jwt Runtimes. See the Authentication section of the Quickstart.
harness deploy builds an image and creates or updates a cloud Runtime, which may incur charges. Updating an existing Runtime also changes its production behavior. Confirm the project, region, configuration, and credential references before deployment, and release changes during an appropriate operational window.
1

Initialize the harness

Create a harness directory containing harness.yaml and .env.example.
2

Configure the agent

Write fields with harness set. Only the flags you pass are modified, so you can build up the configuration across several calls.
To configure a component such as a knowledge base or memory, set its --<component>-type first, then add the connection parameters; pass an empty string "" to disable one. Running agentkit harness set with no flags lists the current fields. See Harness for the full field list.
3

Check cloud settings and component access

Replace your-model-name with a model or endpoint ID available to your account. Default direct model calls require suitable model access on the Runtime role; a successful deployment does not grant model access. Verify a minimal reply without external tools before adding knowledge bases, MCP services, or memoryThis example uses Volcengine Beijing. For BytePlus, initialize with agentkit --provider byteplus harness init my-harness --region ap-southeast-1 and keep deployment and query regions consistent. Reference database passwords and MCP credentials as ${VAR} in harness.yaml, with actual values in an uncommitted .env
4

Build and deploy

Build the image in the cloud from harness.yaml and create or update the runtime.
5

Invoke the runtime

Call the runtime you just deployed by name. The CLI resolves the endpoint and authentication automatically, using configured AK/SK credentials or valid STS credentials from the active SSO login profile.
6

Iterate

Change the configuration and redeploy to publish a new version; when the runtime misbehaves, read the instance logs to diagnose it.
When you no longer need the runtime, delete it to free resources:
Runtime deletion cannot be undone and stops production calls. Confirm the name, project, and region, and retain required configuration, logs, and business data before proceeding.
When you need custom logic, tools, or multi-agent orchestration, use High-code agents instead.
最后修改于 2026年9月19日