Mainly for developers already paying for Z.ai's GLM Coding Plan; the app is free, but the free tier's limits are unclear.
Kenning's take
What it does
ZCode is a desktop app from Z.ai where developers give coding tasks to AI agents, follow their progress and review the changes, with a built-in terminal and Git tools. It is tuned for Z.ai's GLM-5.3 model and uses GLM-5.3-Flash for reading screenshots and images. A Goals feature plans, runs and checks long tasks, and work can be started or steered from WeChat, Feishu or Telegram.
- Multiple agents working on tasks in parallel
- Goals for planning, running and checking long tasks
- Built-in terminal and Git changes view
- Deep integration with GLM-5.3 and GLM-5.3-Flash
- Control from WeChat, Feishu or Telegram
- Downloads for Mac, Windows and Linux (beta)
Who it suits. Developers who use Z.ai's GLM models and want an app to manage coding agents.
Key facts
- Category
- Developer tools
- Made by
- Z.ai
- How to get it
- free download; model use through Z.ai's GLM Coding Plan, and the changelog mentions a free tier
- Works on
- macOS, Windows, Linux (beta)
Pricing
| Plan | Price | Billed |
|---|---|---|
| GLM Coding Lite | $18 (shown discounted to 12.6) | month |
| GLM Coding Pro | $80 (shown discounted to 56) | month |
| GLM Coding Max | $168 (shown discounted to 117.6) | month |
FAQ
Is ZCode free?
The app is a free download. Model use is paid through Z.ai's GLM Coding Plan, which starts at $18 a month before discounts.
Which model does ZCode use?
It is tuned for Z.ai's GLM-5.3, with GLM-5.3-Flash for images and screenshots.
Which platforms does ZCode run on?
Mac and Windows, with Linux in beta.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools

Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.

AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.