Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of ZCode

ZCode

Free Listing

ZCode is Z.ai's AI coding workbench and coding agent harness for complex goals, offering desktop, web, and terminal experiences, multiple agents, GLM-5.3 integration, and remote control from WeChat, Feishu, or Telegram.

Visit zai-org/ZCode

Overview

ZCode is an AI coding workbench from Z.ai that provides desktop, browser, and terminal Agent experiences. It is designed for vibe coding and complex goals, with multiple agents, long-running task management through Goals, and remote control from messaging platforms.

Key Features

  • Long-running tasks: Goals supports continuous planning, execution, and verification for complex work.
  • Bot control: start and steer ZCode from WeChat, Feishu, or Telegram so work can continue anywhere.
  • Deep GLM-5.3 integration: optimized for reasoning, coding, and multi-agent collaboration, with GLM-5.3-Flash built in for multimodal tasks such as screenshot understanding and image analysis.
  • Multiple surfaces: desktop application, browser interface, and terminal Agent, plus a CLI distribution that can run TUI or Web modes.
  • UI Plugin development support, including examples such as Excalidraw canvas collaboration.
  • Shared UI, services, server, RPC, and client SDK packages organized in the repository.

Use Cases

  • Managing complex coding goals with continuous planning, execution, and verification.
  • Steering development work remotely from WeChat, Feishu, or Telegram.
  • Using a terminal or browser interface without Electron for local Agent and Web workflows.
  • Building and testing UI plugins from provided examples and host integration entry points.

Getting Started

  • Download ZCode installers for macOS, Windows, or Linux from the all-downloads section, or read the documentation.
  • For source development, prepare Git, Node.js 24.14.0, and pnpm 10.33.2, then run pnpm bootstrap in the repository root.
  • Run pnpm dev:desktop to start the desktop development workflow.
  • Run zcode for the terminal interface, or zcode --web to start the Web interface.
  • Run pnpm dev:web to start the Web development server and backend together.

Deployment & Requirements

  • Desktop installers are available for macOS Apple Silicon, macOS Intel, Windows 64-bit, Windows ARM64, Linux x64, and Linux ARM64.
  • Source development requires Git, Node.js 24.14.0, and pnpm 10.33.2, with versions defined by mise.toml.
  • The CLI distribution still requires Node.js, with the version defined by mise.toml.
  • Web mode listens on 127.0.0.1 by default, auto-selects a free port, and can bind to other hosts with --host.

Before You Adopt

  • License: Apache-2.0. Review its terms before using, modifying, or distributing the project.
  • Linux x64 downloads are labeled Beta in the source.
  • GLM Coding Plan prices and benefits may change, with final details shown on z.ai.
  • Old Lite users need to switch to the new build commands, environment variables, and install script; new installation does not delete old Lite directories or migrate or delete existing session data.

Comments

Sign in to leave a comment.

More like ZCode

Favicon of Taste Skill

Taste Skill

Free ListingStars: 100.5K

Agent skills that give coding agents taste

Coding Agents

Taste Skill is an open-source Agent Skill that gives coding agents art direction, reference images, and a real-browser check so they build distinctive websites and app screens instead of generic AI pages.

Favicon of Codewhale

Codewhale

Free ListingStars: 41.1K

Open-source coding agent that works with any model.

Coding Agents

Codewhale is an open-source coding agent and terminal client that reads projects, edits files, runs commands, checks its work, and connects to hosted or local models.

Favicon of Caveman

Caveman

Free ListingStars: 113.1K

Make AI agents say less and read less.

Coding Agents

Caveman is an open-source response skill and local CLI proxy for coding agents. It shortens answers and compresses inputs like logs, JSON, CSV, and test output while keeping code, commands, paths, and error messages exact.