Proteus: The AI-native editor for multimodal creation

Published: 1 hour ago (January 1, 2026 at 11:19 PM EST)

2 min read

Source: Dev.to

Overview

I’m building Proteus, an open‑source multimodal editor (think Figma meets Notion) that is AI‑native from day one. AI writes most of the code while I focus on architecture, technical decisions, and quality control.

Why this matters

By 2025 tools like Cursor and Claude can generate good enough code in about 80 % of scenarios. The question shifts from “Can AI code?” to “What becomes valuable when AI can code?” I believe the valuable skills are system design, technical decision‑making, and end‑to‑end ownership—not just knowing APIs.

What makes Proteus different

AI‑native from day one

Every architectural decision prioritizes AI‑friendliness. This isn’t AI bolted on later—it’s designed for AI collaboration from the first line of code.

Fully transparent

All code, architecture decisions, and lessons learned are public. I’m documenting the entire journey in weekly technical articles.

Real editor, not a toy

Phase 1 is complete with a working demo. You can create shapes, text, images, transform them, copy/paste, undo/redo—all the core editor capabilities.

Learning resource

If you want to understand how editors work (scene graphs, rendering, interaction systems) or how to structure code for AI collaboration, this is a live case study.

Current status

✅ Phase 1: Core editing (scene graph, rendering, interaction, tools)
🚧 Phase 2: Multimodal elements (video, audio, web embeds)
📋 Phase 3: AI Agent integration (natural language → editor actions)
📋 Phase 4: Real‑time collaboration

Try it

Live demo:

Code

GitHub repository:

Articles

Tech blog: 4 articles covering architecture, rendering, and interaction design

Experiment

What happens when you stop reviewing AI‑generated code and instead focus entirely on architecture, problem diagnosis, and guiding AI through testing and context‑building? That’s the experiment I’m exploring with Proteus.

Feedback from the community—especially from those building complex frontend apps or thinking about AI‑native development workflows—is welcome.