Cleancode

CleanCode

  简体中文 · 繁體中文 · English · 한국어 · 日本語

  A canvas ADE for human–AI collaboration: AI handles the complexity of learning and operating tools, so you can focus on goals, judgment, and intuitive interaction.
  Work alongside Agents on one canvas, with visible progress and direct control whenever you need it.

  Download CleanCode Preview (macOS / Windows / Linux)

Multiple Agents and connected terminal tasks in a branch workspace.

▶ Multi-Agent Collaboration Demo (0:39)

https://github.com/user-attachments/assets/9e157258-5604-4da6-83f9-65943c19efc5

▶ Full demo (2:33, with sound)

https://github.com/user-attachments/assets/cafe373f-97b7-4f8c-b4a4-dfbc88ab26c3

🧩 What Is CleanCode?

CleanCode is a canvas ADE (Agentic Development Environment) for human–AI collaboration. It brings Agents, terminals, and project workspaces onto one canvas, so you can express intent, interact directly, and work with Agents on development and automation tasks.

Its design draws on System 1 and System 2 from _Thinking, Fast and Slow_: System 1 describes fast, intuitive responses, while System 2 involves focused analysis, planning, and reasoning. CleanCode applies these ideas to human–AI collaboration: people handle System 1 work, while Agents handle System 2 work.

- People focus on intuitive expression and direct interaction. Describe what you want and what you prefer, then observe, select, and adjust on the canvas, retaining control of goals, judgment, and key decisions.
- Agents handle work that requires analysis and planning. Within their tools and permissions, Agents identify available capabilities, learn how to use tools, break down tasks, plan steps, write scripts, configure commands, troubleshoot, and check results.

Completing a task often means learning the software first:…