Skip to main content

CloudBase AI CLI Usage Documentation

Introduction​

CloudBase AI CLI is a unified command-line tool that integrates multiple mainstream AI programming tools, supporting both built-in and custom models.

It enables you to utilize AI programming assistants such as Claude Code, OpenAI Codex, aider, and Qwen Code with a simple command.

It also includes CloudBase AI Toolkit, supporting the complete process from development to deployment, and can run in any environment.

Core Advantages​

  • 🏗️ Unified Management - Manage multiple AI programming CLI tools with a single command, eliminating the need to switch between different tools
  • 🤖 Multi-Model Support - Supports built-in and custom large models, including Kimi K2, Zhipu GLM-4.5, etc.
  • 🚀 One-Click Development and Deployment - Complete process from code generation to cloud deployment, supporting Web applications, Mini Programs, and backend services
  • 🌍 Run Anywhere - Runs in any environment, including Mini Program DevTools, VS Code, GitHub Actions, etc.

Application Scenarios​

Quick Start​

1. Installation​

Recommended: One-click installation script

Completes installation in seconds (compared to several minutes typically required for npm installation), delivering a faster and more convenient experience:

curl https://static.cloudbase.net/cli/install/install.sh  -fsS | bash

2. Initialize AI configuration​

Use the terminal to run the CloudBase AI CLI:

# Start Configuration Wizard
tcb ai

On first launch, the configuration wizard will guide you through:

  • Select AI tool
  • Complete the AI tool configuration

After completing the configuration, you can immediately start using AI tools for assisted development. You can later run tcb ai --setup to switch tools and models.

3. Get Started​

tcb ai

# Or Preset Prompt
tcb ai -- "Help me create an order management system"

# Or use non-interactive mode
tcb ai -- -p "Hello"

# View all available commands
tcb ai --help

Detailed Development Guide​

Refer to the detailed tutorial: Developing a Neighborhood Idle Item Recycling Mini Program Using CloudBase AI CLI

Try it now

Run anywhere, from code generation to cloud deployment!

No API Key required. New environment offers 1 million tokens for free, supporting quick experience with mainstream models like DeepSeek and Kimi K2.

How It Works​

Detailed Usage Instructions​

Basic Commands​

Start AI Tool​

# AI Tool with Default Configuration
tcb ai

# Specifying the AI Tool
tcb ai -a claude 
tcb ai -a codex
tcb ai -a aider
tcb ai -a qwen

Parameter Passthrough​

Use the -- delimiter to pass parameters directly to the target AI tool:

# Pass Parameters to Claude 
tcb ai -a claude -- -p hi

# Equivalent to running claude -p hi

Configuration Management​

View Current Configuration​

tcb ai --config

Reconfigure​

# Reset All Configurations
tcb ai --reset

# Run Configuration Wizard
tcb ai --setup

Supported AI Tools​

AI ToolCommand Parameter
Claude Code-a claude
Openai Codex-a codex
aider-a aider
Qwen Code-a qwen

Get Help​

Command Line Help​

# View Command Help
tcb ai --help

Frequently Asked Questions​

Having problems? Check the CloudBase CLI FAQ for detailed assistance.

Technical Support​

🔥 WeChat Discussion Group​

Encountering issues or want to share experiences? Join our technical community!

WeChat group QR code
Scan the QR code to join the WeChat technical exchange group

Why Choose CLI?​

The CLI turns AI programming capabilities into programmable infrastructure that can be invoked by scripts, automated processes, and CI/CD systems. It eliminates the need to switch between multiple GUI tools and can be integrated into existing development workflows.

Supports cloud-native development, containerized deployment, and continuous integration/continuous deployment (CI/CD), driving the evolution of AI from "code generation" to "full-process collaboration".

Configuration Instructions​

Currently, CloudBase AI CLI supports the configuration of the following AI tools:

  • Claude Code
  • Openai Codex
  • aider
  • Qwen Code

All tools support two configuration methods:

  • Configure a custom LLM: Typically requires configuring your own API KEY and corresponding Base URL
  • Configure an LLM in the Cloud Development environment: No need to configure the API KEY yourself; simply log in and select a Cloud Development environment as prompted by the command line.
AI ToolCustom Configuration RequirementsCloud Development Environment ConfigurationRelevant Documentation
Claude Code- Base URL
- API KEY
- Must be configured as an Anthropic-compatible model
- Supports configuration of Kimi-K2, Zhipu GLM-4.5		✨ One-click login, automatic configurationConfiguration Documentation
OpenAI Codex- Base URL
- API KEY
- Model Name
- Must be configured as an OpenAI-compatible model		✨ One-click login, automatic configurationConfiguration Documentation
aider- Base URL
- API KEY
- Model Name
- Must be configured as an OpenAI-compatible model		✨ One-click login, automatic configurationConfiguration Documentation
Qwen Code- Base URL
- API KEY
- Model Name
- Must be configured as an OpenAI-compatible model		✨ One-click login, automatic configurationConfiguration Documentation