Official Z.ai platform to experience our new, MIT-licensed GLM models (Base, Reasoning, Rumination). Simple UI focuses on model interaction. Free.
This is the 13th launch from Z.ai. View more
ZCode
Launching today
ZCode is the official agentic development environment for GLM-5.2, built for long-running coding tasks with stable context, file edits, terminal and browser state, Git review, mobile Remote, bot control, BYOK, and macOS, Windows, and Linux apps.
Free Options
Launch Team
Hugging Face
Flowtica Scribe
Hi everyone!
Have been using ZCode since its first version late last year. With the recent 3.0 upgrade, it's taken a massive leap forward. Here are a few reasons it’s worth a try:
It’s the official harness for GLM-5.2. Yes, try the tuning that understands the true upper bound of GLM-5.2 better than anything else!
It’s built for long-horizon execution. The in-house ZCode Agent keeps your files, terminal output, browser context, and Git state stitched together in the same task loop, so it doesn't lose the thread halfway through a complex build.
It lets you step away from the desk. You can steer the agent, check progress, and kick off tasks from your phone, or directly through messaging bots while the desktop keeps running.
And it’s moving fast!
Congrats on the launch! 🚀
Long-running coding agents are where things usually get difficult, especially when the agent has to keep file state, terminal output, browser context, and Git changes aligned across one task.
Curious how ZCode handles situations where the agent gets stuck or starts making risky edits. Does it surface checkpoints or risk summaries before continuing?
Tried the reasoning model on a coding problem and it nailed a tricky edge case I'd been stuck on for an hour. Really appreciate that the base models are MIT-licensed, makes it easy to experiment locally without worrying about restrictions.
Curious how the rumination model handles long context sessions compared to the base version?
the minimalist UI actually lets the models breathe instead of competing with them. nice to see a platform that trusts the work to speak for itself.