> ## Documentation Index
> Fetch the complete documentation index at: https://docs.veadk.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

`agentkit` is the command-line tool for AgentKit, built around the full
lifecycle of an agent: scaffold a project, build and deploy its runtime, invoke
the deployed agent, and manage the MCP services, knowledge bases, memory,
sandboxes, skills, and evaluation it relies on — all from your terminal.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/productions/agentkit-cli/preview/en/quickstart">
    Install, configure credentials, deploy, and verify your first agent
  </Card>

  <Card title="Command reference" icon="terminal" href="/productions/agentkit-cli/preview/en/commands">
    Find command purposes, parameters, defaults, and examples
  </Card>
</CardGroup>

## Command groups

| Group | What it manages |
| - | - |
| `init` | scaffold a new agent project |
| `config` | manage project lifecycle config and user-wide defaults |
| `build` | build a runtime image from lifecycle config |
| `deploy` | deploy an already built runtime from lifecycle config |
| `launch` | build and deploy a lifecycle project in one command |
| `status` | show runtime state for the current project |
| `release` | run the full cloud release pipeline from `.agentkit/agentkit.yaml` |
| `runtime` | deployed runtimes (list, show, logs, versions, release, update, delete) |
| `knowledge` (`kb`) | knowledge bases |
| `memory` (`mem`) | memory collections |
| `model-gateway` (`mgw`) | unified model gateway, model providers, and consumers |
| `user` | User-pool users |
| `department` | Department hierarchy and membership |
| `group` | User-pool groups |
| `harness` | Configure, deploy, invoke Harness, and manage scheduled tasks |
| `chat` | chat with shared OAuth Harnesses through tenant aliases |
| `invoke` | call a deployed runtime |
| `auth` | Console and SSO login, identity, login profiles, and organization SSO setup |
| `onboard` | install bundled skills into local coding agents |
| `eval` | evaluation backend, datasets, evaluators, targets, and experiments |
| `migrate` | migrate an existing agent application to AgentKit |
| `mcp service` | create, inspect, and delete MCP services |
| `sandbox` | run commands and manage sessions in a sandbox |
| `env` (`environment`) | manage the Runtime for Claude self-host sandbox environments |
| `skill` | skills on the AgentKit skill platform |
| `skills` | Upload, download, generate wrappers, and publish paired skills |
| `destroy` | delete a deployed runtime |
| `upgrade` | check for and install AgentKit CLI updates |
| `tree` | print the command tree |
| `docs` | open or print the AgentKit CLI documentation URL |

## Conventions

* `agentkit` may also be invoked as `ak`.
* `login`, `logout`, and `whoami` are available as top-level commands and as
  `auth login`, `auth logout`, and `auth whoami`.
* `knowledge` has aliases `kb` and `knowledgebase`, `memory` has alias `mem`,
  `model-gateway` has alias `mgw`, `env` has alias `environment`, `skills secure` converts local skill packages, and the `eval` prefix is optional (`agentkit dataset …` is equivalent to
  `agentkit eval dataset …`).
* Most read commands accept `--json`. Regions resolve from the provider and configuration. Check each command before overriding them: short options vary, and `invoke run -r` selects a Runtime ID
* Every product command accepts global `--provider volcengine|byteplus` to
  override the cloud provider for that command.
* Deletion behavior is command-specific. Most delete commands require confirmation; `sandbox snapshot delete` deletes immediately and has no `--yes` option