vm0-cli

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

VM0 CLI

Build and run AI agents in secure sandboxed environments using the VM0 command-line interface.

Official docs: https://docs.vm0.ai

使用VM0命令行界面在安全沙箱环境中构建和运行AI Agent。

官方文档：https://docs.vm0.ai

When to Use

适用场景

Use this skill when you need to:

Install and set up the VM0 CLI
Create and configure AI agent projects
Deploy agents to the VM0 platform
Run agents with prompts and inputs
Manage input files (volumes) and output files (artifacts)
View logs and usage statistics

当你需要以下操作时，可使用该工具：

安装和配置VM0 CLI
创建和配置AI Agent项目
将Agent部署到VM0平台
通过提示词和输入运行Agent
管理输入文件（卷）和输出文件（制品）
查看日志和使用统计数据

Prerequisites

前置条件

Installation

安装步骤

Install the VM0 CLI globally via npm:

bash

npm install -g @vm0/cli

Verify installation:

bash

vm0 --version

通过npm全局安装VM0 CLI：

bash

npm install -g @vm0/cli

验证安装：

bash

vm0 --version

Authentication

身份验证

bash

vm0 auth login

This opens a browser for authentication. After login, verify status:

bash

vm0 auth status

For CI/CD environments, get your API token:

bash

vm0 auth setup-token

Then set the environment variable:

bash

export VM0_TOKEN=vm0_live_your-api-key

登录你的VM0账户：

bash

vm0 auth login

这会打开浏览器进行身份验证。登录后，验证状态：

bash

vm0 auth status

对于CI/CD环境，获取你的API令牌：

bash

vm0 auth setup-token

然后设置环境变量：

bash

export VM0_TOKEN=vm0_live_your-api-key

Quick Start

快速开始

1. Initialize a Project

1. 初始化项目

Create a new VM0 project in the current directory:

bash

vm0 init

This creates a

vm0.yaml

configuration file interactively. For non-interactive mode:

bash

vm0 init --name my-agent

在当前目录创建一个新的VM0项目：

bash

vm0 init

这会以交互方式创建一个

vm0.yaml

配置文件。非交互模式：

bash

vm0 init --name my-agent

2. Configure the Agent

2. 配置Agent

Edit

vm0.yaml

to define your agent:

yaml

version: "1.0"

agents:
  my-agent:
    framework: claude-code
    instructions: AGENTS.md
    skills:
      - https://github.com/vm0-ai/vm0-skills/tree/main/github
    environment:
      DEBUG: "${{ vars.DEBUG }}"
      API_KEY: "${{ secrets.API_KEY }}"

编辑

vm0.yaml

来定义你的Agent：

yaml

version: "1.0"

agents:
  my-agent:
    framework: claude-code
    instructions: AGENTS.md
    skills:
      - https://github.com/vm0-ai/vm0-skills/tree/main/github
    environment:
      DEBUG: "${{ vars.DEBUG }}"
      API_KEY: "${{ secrets.API_KEY }}"

3. Deploy the Agent

3. 部署Agent

Deploy your agent configuration:

bash

vm0 compose vm0.yaml

Skip confirmation prompts with

-y

bash

vm0 compose vm0.yaml -y

部署你的Agent配置：

bash

vm0 compose vm0.yaml

使用

-y

跳过确认提示：

bash

vm0 compose vm0.yaml -y

4. Run the Agent

4. 运行Agent

Execute the agent with a prompt:

bash

vm0 run my-agent "Please analyze the codebase and suggest improvements"

Or use

cook

for one-click execution from

vm0.yaml

bash

vm0 cook "Analyze the code"

通过提示词执行Agent：

bash

vm0 run my-agent "Please analyze the codebase and suggest improvements"

或者使用

cook

命令从

vm0.yaml

一键执行：

bash

vm0 cook "Analyze the code"

Core Operations

核心操作

Running Agents

运行Agent

Basic run:

bash

vm0 run my-agent "Your prompt here"

Run with variables and secrets:

bash

vm0 run my-agent "Process data" --vars DEBUG=true --secrets API_KEY=xxx

Run with environment file:

bash

vm0 run my-agent "Process data" --env-file=.env.local

Load environment variables from a file. The file should contain

KEY=value

pairs (one per line). This is useful for local development when you don't want to use the

${{ secrets.* }}

syntax in

vm0.yaml

Example

.env.local

file:

bash

GH_TOKEN=github_pat_xxx
API_KEY=sk-xxx
SLACK_WEBHOOK_URL=https://hooks.slack.com/services/xxx

Run with artifact storage:

bash

vm0 run my-agent "Generate report" --artifact-name my-output

Run with input volumes:

bash

vm0 run my-agent "Process files" --volume-version input-data=latest

Enable verbose output:

bash

vm0 run my-agent "Hello" -v

Resume from checkpoint:

bash

vm0 run resume <checkpoint-id> "Continue the task"

Continue from session:

bash

vm0 run continue <session-id> "Next step"

基础运行：

bash

vm0 run my-agent "Your prompt here"

带变量和密钥运行：

bash

vm0 run my-agent "Process data" --vars DEBUG=true --secrets API_KEY=xxx

带环境文件运行：

bash

vm0 run my-agent "Process data" --env-file=.env.local

从文件加载环境变量。文件应包含

KEY=value

格式的键值对（每行一个）。这在本地开发中很有用，你无需在

vm0.yaml

中使用

${{ secrets.* }}

语法。

示例

.env.local

文件：

bash

GH_TOKEN=github_pat_xxx
API_KEY=sk-xxx
SLACK_WEBHOOK_URL=https://hooks.slack.com/services/xxx

带制品存储运行：

bash

vm0 run my-agent "Generate report" --artifact-name my-output

带输入卷运行：

bash

vm0 run my-agent "Process files" --volume-version input-data=latest

启用详细输出：

bash

vm0 run my-agent "Hello" -v

从检查点恢复：

bash

vm0 run resume <checkpoint-id> "Continue the task"

从会话继续：

bash

vm0 run continue <session-id> "Next step"

One-Click Execution (cook)

一键执行（cook）

Run directly from

vm0.yaml

in current directory:

bash

vm0 cook "Your prompt"

Skip confirmation:

bash

vm0 cook -y "Your prompt"

Run with environment file:

bash

vm0 cook --env-file=.env.local "Your prompt"

Load environment variables from a file for the agent run. Combine with

-y

to skip confirmation:

bash

vm0 cook -y --env-file=.env.local "Your prompt"

Continue last session:

bash

vm0 cook continue "Follow up"

Resume from last checkpoint:

bash

vm0 cook resume "Continue"

View logs from last cook run:

bash

vm0 cook logs

直接从当前目录的

vm0.yaml

运行：

bash

vm0 cook "Your prompt"

跳过确认：

bash

vm0 cook -y "Your prompt"

带环境文件运行：

bash

vm0 cook --env-file=.env.local "Your prompt"

从文件加载环境变量用于Agent运行。结合

-y

跳过确认：

bash

vm0 cook -y --env-file=.env.local "Your prompt"

继续上一个会话：

bash

vm0 cook continue "Follow up"

从最后一个检查点恢复：

bash

vm0 cook resume "Continue"

查看上一次cook运行的日志：

bash

vm0 cook logs

Viewing Logs

查看日志

View agent events (default):

bash

vm0 logs <run-id>

View system logs:

bash

vm0 logs <run-id> --system

View metrics:

bash

vm0 logs <run-id> --metrics

View network logs:

bash

vm0 logs <run-id> --network

Filter by time:

bash

vm0 logs <run-id> --since 5m
vm0 logs <run-id> --since 2h
vm0 logs <run-id> --since 2024-01-15T10:30:00Z

Show last N entries:

bash

vm0 logs <run-id> --tail 20

查看Agent事件（默认）：

bash

vm0 logs <run-id>

查看系统日志：

bash

vm0 logs <run-id> --system

查看指标：

bash

vm0 logs <run-id> --metrics

查看网络日志：

bash

vm0 logs <run-id> --network

按时间过滤：

bash

vm0 logs <run-id> --since 5m
vm0 logs <run-id> --since 2h
vm0 logs <run-id> --since 2024-01-15T10:30:00Z

显示最后N条记录：

bash

vm0 logs <run-id> --tail 20

Storage Management

存储管理

Volumes (Input Files)

卷（输入文件）

Volumes store input files that agents can read.

Initialize a volume (interactive):

bash

cd my-data-directory
vm0 volume init

Initialize a volume (non-interactive):

bash

cd my-data-directory
vm0 volume init --name my-data

Push local files to cloud:

bash

vm0 volume push

Pull cloud files to local:

bash

vm0 volume pull

Pull specific version:

bash

vm0 volume pull abc123de

Check volume status:

bash

vm0 volume status

List all volumes:

bash

vm0 volume list

Clone a remote volume:

bash

vm0 volume clone my-volume ./local-dir

卷用于存储Agent可以读取的输入文件。

初始化卷（交互模式）：

bash

cd my-data-directory
vm0 volume init

初始化卷（非交互模式）：

bash

cd my-data-directory
vm0 volume init --name my-data

将本地文件推送到云端：

bash

vm0 volume push

将云端文件拉取到本地：

bash

vm0 volume pull

拉取特定版本：

bash

vm0 volume pull abc123de

检查卷状态：

bash

vm0 volume status

列出所有卷：

bash

vm0 volume list

克隆远程卷：

bash

vm0 volume clone my-volume ./local-dir

Artifacts (Output Files)

制品（输出文件）

Artifacts store output files created by agents.

Initialize an artifact (interactive):

bash

cd my-output-directory
vm0 artifact init

Initialize an artifact (non-interactive):

bash

cd my-output-directory
vm0 artifact init --name my-output

Push local files to cloud:

bash

vm0 artifact push

Pull cloud files to local:

bash

vm0 artifact pull

Pull specific version:

bash

vm0 artifact pull abc123de

Check artifact status:

bash

vm0 artifact status

List all artifacts:

bash

vm0 artifact list

Clone a remote artifact:

bash

vm0 artifact clone my-artifact ./local-dir

制品用于存储Agent生成的输出文件。

初始化制品（交互模式）：

bash

cd my-output-directory
vm0 artifact init

初始化制品（非交互模式）：

bash

cd my-output-directory
vm0 artifact init --name my-output

将本地文件推送到云端：

bash

vm0 artifact push

将云端文件拉取到本地：

bash

vm0 artifact pull

拉取特定版本：

bash

vm0 artifact pull abc123de

检查制品状态：

bash

vm0 artifact status

列出所有制品：

bash

vm0 artifact list

克隆远程制品：

bash

vm0 artifact clone my-artifact ./local-dir

Agent Management

Agent管理

List Agents

列出Agent

bash

vm0 agent list

With details:

bash

vm0 agent list --verbose

bash

vm0 agent list

查看详细信息：

bash

vm0 agent list --verbose

Inspect Agent

检查Agent

View agent configuration:

bash

vm0 agent inspect my-agent

View specific version:

bash

vm0 agent inspect my-agent:abc123

查看Agent配置：

bash

vm0 agent inspect my-agent

查看特定版本：

bash

vm0 agent inspect my-agent:abc123

Clone Agent

克隆Agent

Download an agent's compose configuration to local directory:

bash

vm0 agent clone my-agent

Clone to a specific directory:

bash

vm0 agent clone my-agent ./my-project

This command:

Downloads compose configuration and saves as
```
vm0.yaml
```
Downloads instructions file (e.g.,
```
AGENTS.md
```
) if exists
Preserves environment variables with
```
${{ secrets.X }}
```
syntax
Fails if destination directory already exists

将Agent的compose配置下载到本地目录：

bash

vm0 agent clone my-agent

克隆到指定目录：

bash

vm0 agent clone my-agent ./my-project

该命令会：

下载compose配置并保存为
```
vm0.yaml
```
如果存在说明文件（如
```
AGENTS.md
```
）则一并下载
保留使用
```
${{ secrets.X }}
```
语法的环境变量
如果目标目录已存在则执行失败

Usage Statistics

使用统计

View your usage statistics:

bash

vm0 usage

Filter by date range:

bash

vm0 usage --since 7d
vm0 usage --since 30d
vm0 usage --since 2024-01-01 --until 2024-01-31

查看你的使用统计数据：

bash

vm0 usage

按日期范围过滤：

bash

vm0 usage --since 7d
vm0 usage --since 30d
vm0 usage --since 2024-01-01 --until 2024-01-31

Model Provider Configuration

模型提供商配置

Manage LLM model providers for agent runs.

管理用于Agent运行的LLM模型提供商。

Supported Provider Types

支持的提供商类型

Type	Description
`anthropic-api-key`	Anthropic API key (Claude models)
`openrouter-api-key`	OpenRouter API with auto model routing
`moonshot-api-key`	Moonshot AI (Kimi) API key
`minimax-api-key`	MiniMax API key

List providers:

bash

vm0 model-provider list

Setup a provider (interactive):

bash

vm0 model-provider setup

Setup a provider (non-interactive):

bash

vm0 model-provider setup --type anthropic-api-key --credential "sk-ant-xxx"

Set default provider:

bash

vm0 model-provider set-default anthropic-api-key

Delete a provider:

bash

vm0 model-provider delete anthropic-api-key

类型	描述
`anthropic-api-key`	Anthropic API密钥（Claude模型）
`openrouter-api-key`	OpenRouter API，支持自动模型路由
`moonshot-api-key`	月之暗面AI（Kimi）API密钥
`minimax-api-key`	MiniMax API密钥

列出提供商：

bash

vm0 model-provider list

设置提供商（交互模式）：

bash

vm0 model-provider setup

设置提供商（非交互模式）：

bash

vm0 model-provider setup --type anthropic-api-key --credential "sk-ant-xxx"

设置默认提供商：

bash

vm0 model-provider set-default anthropic-api-key

删除提供商：

bash

vm0 model-provider delete anthropic-api-key

OpenRouter Provider

OpenRouter提供商

OpenRouter supports multiple model providers through a single API. Two modes available:

Auto mode (default): OpenRouter automatically routes to the best available model.

bash

vm0 model-provider setup --type openrouter-api-key --credential "sk-or-xxx"

Explicit model selection: Specify a model from supported list.

bash

vm0 model-provider setup --type openrouter-api-key --credential "sk-or-xxx" --model anthropic/claude-sonnet-4.5

Supported models include Claude (anthropic/claude-), Kimi (moonshotai/kimi-), DeepSeek (deepseek/), GLM (z-ai/glm-), MiniMax (minimax/), and Qwen (qwen/) series.

OpenRouter通过单一API支持多个模型提供商，提供两种模式：

自动模式（默认）： OpenRouter自动路由到最佳可用模型。

bash

vm0 model-provider setup --type openrouter-api-key --credential "sk-or-xxx"

显式模型选择： 从支持的列表中指定模型。

bash

vm0 model-provider setup --type openrouter-api-key --credential "sk-or-xxx" --model anthropic/claude-sonnet-4.5

支持的模型包括Claude（anthropic/claude-）、Kimi（moonshotai/kimi-）、DeepSeek（deepseek/）、GLM（z-ai/glm-）、MiniMax（minimax/）和Qwen（qwen/）系列。

Secret Management

密钥管理

Store secrets remotely for agent runs. Secrets are for sensitive values (API keys, tokens) and are referenced in vm0.yaml as

${{ secrets.NAME }}

List secrets:

bash

vm0 secret list

Set a secret (interactive — prompts for value):

bash

vm0 secret set MY_API_KEY

Set a secret (non-interactive):

bash

vm0 secret set MY_API_KEY --body "sk-xxx-secret-value"

Set a secret with description:

bash

vm0 secret set MY_API_KEY --body "sk-xxx" --description "OpenAI API key for summarization"

Delete a secret:

bash

vm0 secret delete MY_API_KEY

Delete without confirmation:

bash

vm0 secret delete MY_API_KEY -y

为Agent运行远程存储密钥。密钥用于存储敏感值（API密钥、令牌），在vm0.yaml中通过

${{ secrets.NAME }}

引用。

列出密钥：

bash

vm0 secret list

设置密钥（交互模式 — 提示输入值）：

bash

vm0 secret set MY_API_KEY

设置密钥（非交互模式）：

bash

vm0 secret set MY_API_KEY --body "sk-xxx-secret-value"

设置带描述的密钥：

bash

vm0 secret set MY_API_KEY --body "sk-xxx" --description "OpenAI API key for summarization"

删除密钥：

bash

vm0 secret delete MY_API_KEY

无需确认直接删除：

bash

vm0 secret delete MY_API_KEY -y

Variable Management

变量管理

Store variables remotely for agent runs. Variables are for non-sensitive configuration and are referenced in vm0.yaml as

${{ vars.NAME }}

List variables:

bash

vm0 variable list

Set a variable:

bash

vm0 variable set DEBUG true

Set a variable with description:

bash

vm0 variable set ENV_NAME production --description "Target environment"

Delete a variable:

bash

vm0 variable delete DEBUG

Delete without confirmation:

bash

vm0 variable delete ENV_NAME -y

为Agent运行远程存储变量。变量用于非敏感配置，在vm0.yaml中通过

${{ vars.NAME }}

引用。

列出变量：

bash

vm0 variable list

设置变量：

bash

vm0 variable set DEBUG true

设置带描述的变量：

bash

vm0 variable set ENV_NAME production --description "Target environment"

删除变量：

bash

vm0 variable delete DEBUG

无需确认直接删除：

bash

vm0 variable delete ENV_NAME -y

vm0.yaml Reference

vm0.yaml 参考文档

Basic Structure

基本结构

yaml

version: "1.0"

agents:
  agent-name:
    framework: claude-code
    instructions: AGENTS.md
    skills:
      - https://github.com/vm0-ai/vm0-skills/tree/main/github
      - https://github.com/vm0-ai/vm0-skills/tree/main/slack
    environment:
      VAR_NAME: "value"
      SECRET_VAR: "${{ secrets.SECRET_NAME }}"
      CONFIG_VAR: "${{ vars.CONFIG_NAME }}"

yaml

version: "1.0"

agents:
  agent-name:
    framework: claude-code
    instructions: AGENTS.md
    skills:
      - https://github.com/vm0-ai/vm0-skills/tree/main/github
      - https://github.com/vm0-ai/vm0-skills/tree/main/slack
    environment:
      VAR_NAME: "value"
      SECRET_VAR: "${{ secrets.SECRET_NAME }}"
      CONFIG_VAR: "${{ vars.CONFIG_NAME }}"

Fields

字段说明

Field	Description
`version`	Configuration version (currently "1.0")
`agents`	Map of agent definitions
`framework`	Agent framework (e.g., `claude-code` )
`instructions`	Path to instructions file
`skills`	List of skill URLs to include
`environment`	Environment variables for the agent

字段	描述
`version`	配置版本（当前为"1.0"）
`agents`	Agent定义的映射
`framework`	Agent框架（例如 `claude-code` ）
`instructions`	说明文件的路径
`skills`	要包含的技能URL列表
`environment`	Agent的环境变量

Variable Syntax

变量语法

```
${{ secrets.NAME }}
```
- Sensitive values stored securely
```
${{ vars.NAME }}
```
- Non-sensitive configuration values
Direct values - Plain text values

```
${{ secrets.NAME }}
```
- 安全存储的敏感值
```
${{ vars.NAME }}
```
- 非敏感配置值
直接值 - 纯文本值

Environment Information

环境信息

View system and environment details:

bash

vm0 info

查看系统和环境详情：

bash

vm0 info

Non-Interactive Mode (CI/CD)

非交互模式（CI/CD）

All commands support non-interactive mode for use in CI/CD pipelines, scripts, and automated environments. The CLI detects non-TTY environments (

process.stdout.isTTY === false

) and requires explicit flags for all inputs.

所有命令都支持非交互模式，适用于CI/CD流水线、脚本和自动化环境。CLI会检测非TTY环境（

process.stdout.isTTY === false

），并要求所有输入使用显式标志。

Authentication

身份验证

Set the

VM0_TOKEN

environment variable instead of interactive login:

bash

export VM0_TOKEN=vm0_live_your-api-key

设置

VM0_TOKEN

环境变量以替代交互式登录：

bash

export VM0_TOKEN=vm0_live_your-api-key

Command Reference

命令参考

Command	Non-Interactive Flags	Notes
`vm0 init`	`--name <name>`	Required in non-TTY
`vm0 compose`	`-y, --yes`	Skip new secrets confirmation
`vm0 run`	`--env-file <file>`	Load environment variables from file
`vm0 cook`	`-y, --yes` , `--env-file <file>`	Skip prompts; load env vars from file
`vm0 volume init`	`--name <name>`	Required in non-TTY
`vm0 artifact init`	`--name <name>`	Required in non-TTY
`vm0 schedule init`	`--name` , `--frequency` , `--time` , `--prompt`	All required; `--day` for weekly/monthly
`vm0 schedule delete`	`-f, --force`	Skip deletion confirmation
`vm0 secret set`	`-b, --body <value>`	Required in non-TTY
`vm0 secret delete`	`-y, --yes`	Skip confirmation
`vm0 variable delete`	`-y, --yes`	Skip confirmation
`vm0 model-provider setup`	`--type <type> --credential <value>`	Both required together

命令	非交互标志	说明
`vm0 init`	`--name <name>`	非TTY环境下必填
`vm0 compose`	`-y, --yes`	跳过新密钥确认
`vm0 run`	`--env-file <file>`	从文件加载环境变量
`vm0 cook`	`-y, --yes` , `--env-file <file>`	跳过提示；从文件加载环境变量
`vm0 volume init`	`--name <name>`	非TTY环境下必填
`vm0 artifact init`	`--name <name>`	非TTY环境下必填
`vm0 schedule init`	`--name` , `--frequency` , `--time` , `--prompt`	全部必填；每周/每月计划需加 `--day`
`vm0 schedule delete`	`-f, --force`	跳过删除确认
`vm0 secret set`	`-b, --body <value>`	非TTY环境下必填
`vm0 secret delete`	`-y, --yes`	跳过确认
`vm0 variable delete`	`-y, --yes`	跳过确认
`vm0 model-provider setup`	`--type <type> --credential <value>`	两者需同时提供

CI/CD Example

CI/CD示例

bash

undefined

bash

undefined

Set authentication

设置身份验证

export VM0_TOKEN=${{ secrets.VM0_TOKEN }}

Initialize project (non-interactive)

初始化项目（非交互模式）

vm0 init --name my-agent --force

Initialize storage (non-interactive)

初始化存储（非交互模式）

cd input-data && vm0 volume init --name input-data && cd .. cd artifact && vm0 artifact init --name artifact && cd ..

Deploy agent (skip confirmation)

部署Agent（跳过确认）

vm0 compose vm0.yaml -y

Run agent with environment file

带环境文件运行Agent

vm0 run my-agent --artifact-name artifact --env-file=.env.local "Execute the task"

undefined

vm0 run my-agent --artifact-name artifact --env-file=.env.local "Execute the task"

undefined

GitHub Actions Example

GitHub Actions示例

yaml

jobs:
  run-agent:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: "20"

      - name: Install VM0 CLI
        run: npm install -g @vm0/cli

      - name: Run Agent
        env:
          VM0_TOKEN: ${{ secrets.VM0_TOKEN }}
        run: |
          vm0 compose vm0.yaml -y
          vm0 run my-agent --artifact-name output --env-file=.env "Generate daily report"

yaml

jobs:
  run-agent:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Setup Node.js
        uses: actions/setup-node@v4
        with:
          node-version: "20"

      - name: Install VM0 CLI
        run: npm install -g @vm0/cli

      - name: Run Agent
        env:
          VM0_TOKEN: ${{ secrets.VM0_TOKEN }}
        run: |
          vm0 compose vm0.yaml -y
          vm0 run my-agent --artifact-name output --env-file=.env "Generate daily report"

Model Provider Setup (Non-Interactive)

模型提供商设置（非交互模式）

bash

vm0 model-provider setup --type anthropic-api-key --credential "sk-ant-xxx"

bash

vm0 model-provider setup --type anthropic-api-key --credential "sk-ant-xxx"

Guidelines

使用指南

Always authenticate first - Run
```
vm0 auth login
```
before using other commands
Use
vm0 init
for new projects - Creates proper project structure
Deploy before running - Run
```
vm0 compose
```
after modifying
```
vm0.yaml
```
Use volumes for input data - Push data files as volumes before running agents
Check logs for debugging - Use
```
vm0 logs
```
to troubleshoot failed runs
Use scopes for organization - Set appropriate scope for team collaboration

始终先进行身份验证 - 使用其他命令前先运行
```
vm0 auth login
```
使用
vm0 init
创建新项目 - 生成正确的项目结构
运行前先部署 - 修改
```
vm0.yaml
```
后运行
```
vm0 compose
```
使用卷存储输入数据 - 运行Agent前将数据文件推送到卷中
查看日志进行调试 - 使用
```
vm0 logs
```
排查运行失败问题
使用作用域进行组织 - 为团队协作设置合适的作用域

Common Workflows

常见工作流

Deploy and Run Agent

部署并运行Agent

bash

undefined

bash

undefined

1. Initialize project

1. 初始化项目

vm0 init --name my-agent

2. Edit vm0.yaml and AGENTS.md

2. 编辑vm0.yaml和AGENTS.md

3. Deploy configuration

3. 部署配置

vm0 compose vm0.yaml

4. Run the agent

4. 运行Agent

vm0 run my-agent "Execute the task"

5. Check logs if needed

5. 必要时查看日志

vm0 logs <run-id>

undefined

vm0 logs <run-id>

undefined

Provide Input Files to Agent

为Agent提供输入文件

bash

undefined

bash

undefined

1. Create and navigate to data directory

1. 创建并进入数据目录

mkdir input-data && cd input-data

2. Add your files

2. 添加你的文件

cp ~/documents/*.pdf .

3. Initialize and push volume (use --name for non-interactive)

3. 初始化并推送卷（非交互模式使用--name）

vm0 volume init --name input-data vm0 volume push

4. Run agent with volume

4. 带卷运行Agent

cd .. vm0 run my-agent "Process the documents" --volume-version input-data=latest

undefined

cd .. vm0 run my-agent "Process the documents" --volume-version input-data=latest

undefined

Download Agent Output

下载Agent输出

bash

undefined

bash

undefined

1. List artifacts

1. 列出制品

vm0 artifact list

2. Clone the artifact locally

2. 将制品克隆到本地

vm0 artifact clone my-output ./results

3. Or pull to existing directory

3. 或者拉取到现有目录

cd my-output-dir vm0 artifact pull

---

cd my-output-dir vm0 artifact pull

---

Troubleshooting

故障排查

Authentication Issues

身份验证问题

bash

undefined

bash

undefined

Check auth status

检查身份验证状态

vm0 auth status

Re-login if needed

必要时重新登录

vm0 auth logout vm0 auth login

undefined

vm0 auth logout vm0 auth login

undefined

Agent Not Found

Agent未找到

bash

undefined

bash

undefined

List available agents

列出可用Agent

vm0 agent list

Check if deployed

检查是否已部署

vm0 compose vm0.yaml

undefined

vm0 compose vm0.yaml

undefined

View Detailed Errors

查看详细错误

bash

undefined

bash

undefined

Use verbose mode

使用详细模式

vm0 run my-agent "prompt" -v

Check system logs

检查系统日志

vm0 logs <run-id> --system

undefined

vm0 logs <run-id> --system

undefined