zai-cli

jeremylongshore's avatarfrom jeremylongshore

Z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP.Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis,real-time web search, web page to markdown extraction, or GitHub code exploration.Trigger with phrases like "analyze this image", "search the web for", "read this page","explore this repo", or "use zai". Requires Z_AI_API_KEY.

⭐878stars🔀101forks📁View on GitHub🕐Updated Jan 4, 2026

When & Why to Use This Skill

Zai CLI is a powerful Claude skill that integrates advanced vision, real-time web search, and GitHub exploration capabilities via the Model Context Protocol (MCP). It empowers developers and researchers to perform OCR, analyze images or videos, convert UI designs to code, and extract clean markdown from web pages, significantly expanding the functional boundaries of AI agents.

Use Cases

  • Frontend Development: Accelerate the development cycle by converting UI screenshots or design mockups into functional code snippets using vision-to-code capabilities.
  • Technical Research: Conduct real-time web searches and extract high-quality markdown from technical documentation or articles for deep analysis and summarization.
  • Codebase Exploration: Navigate and understand complex GitHub repositories to diagnose errors, perform code reviews, or learn implementation patterns directly through the CLI.
  • Visual Content Analysis: Utilize OCR and video analysis to process non-textual data, enabling the AI to interpret charts, handwritten notes, or video demonstrations for reporting.
namezai-cli
description|
allowed-toolsRead, Write, Edit, Bash(cmd:*), WebFetch
version1.0.0
licenseApache-2.0
authorNumman Ali <numman.ali@gmail.com>

Zai Cli

Overview

ZAI CLI provides access to Z.AI capabilities including image/video analysis, real-time web search, web page extraction, and GitHub code exploration. It integrates with Claude Code via MCP protocol for seamless AI-powered content analysis.

Prerequisites

Instructions

  1. Obtain an API key from Z.AI platform
  2. Export your API key: export Z_AI_API_KEY="your-key"
  3. Run npx zai-cli doctor to verify setup
  4. Use npx zai-cli --help to see available commands
  5. Try basic commands like vision, search, read, or repo
  6. Use --help on any subcommand for detailed options

Access Z.AI capabilities via npx zai-cli. The CLI is self-documenting - use --help at any level.

Output

Default: data-only (raw output for token efficiency). Use --output-format json for { success, data, timestamp } wrapping.

Error Handling

See {baseDir}/references/errors.md for comprehensive error handling.

Examples

See {baseDir}/references/examples.md for detailed examples.

Resources