My Craziest Side Project Yet: Drawva

Fullstack developer Taqui built Drawva, an open-source infinite-canvas whiteboard engine that uses a multimodal AI perception agent to interpret freehand sketches and convert them into live diagrams, interactive code widgets, and math equations. The system runs a modular DeepSeek Harness on a Cordis microkernel runtime, with 11 dynamically loaded plugins, 7 sandboxed diagram runtimes (Mermaid, Graphviz DOT, Vega-Lite, SMILES, BPMN, Cytoscape, GeoJSON), MathJax LaTeX typesetting, IndexedDB autosave, and peer-to-peer WebRTC collaboration without central server databases.

This is a submission for the MLH x DEV Writing Challenge https://dev.to/mlh-hackathon Hey there, my name is Taqui https://taqui.in/ . I am a fullstack web developer. When I started coding back in 2020, things were simple and skills had the highest priority. Lately, with the rapid rise of AI and the tough job market, I have felt pretty cookeddd. But instead of sitting back and questioning my career choice, I decided to dive headfirst into Agentic AI and GenAI to build a serious, real-world system from scratch. That project is Drawva . Drawva is an infinite canvas whiteboard engine powered by a multimodal AI perception agent. Unlike typical whiteboards where your strokes are just static pixels, Drawva actually looks at your canvas, understands your hand-drawn gestures, and turns them into live diagrams, interactive code widgets, and math equations. Under the hood, Drawva runs a modular DeepSeek Harness system built on a Cordis microkernel runtime: canvas apply , canvas snapshot , canvas read , canvas patch widget . Getting an LLM to accurately interact with a freehand 2D canvas required custom prompt engineering contracts: Drawva features 11 extensible runtime plugins loaded dynamically via load plugin : Drawva supports 7 sandboxed diagram runtimes Mermaid, Graphviz DOT, Vega-Lite charts, SMILES molecular structures, BPMN, Cytoscape, GeoJSON alongside MathJax LaTeX typesetting. Everything autosaves to IndexedDB, and users can collaborate peer-to-peer over WebRTC with zero central server databases. Here is a full walkthrough video showing Drawva in action, from freehand sketching to live diagram rendering: Direct video link: Drawva Demo on YouTube https://youtu.be/MM1mFiCGg6w Building Drawva pushed me to integrate modern fullstack and AI technologies: Tbh this was my first hackathon 😅. And Over the past few months, I had been losing my confidence as a developer, wondering if AI was making my hard-earned skills obsolete. Building Drawva was not the only goad for this hackathon. The main purpose is that new Deepseek Harness in the market and it is opensources, So i decided to learn how the harness is build and end up integrating the mini-kernal in this project. This experience proved to me that as developers, our value is not gone. We just have to evolve, pick up Agentic AI, and build ambitious tools that solve real problems. Look, the tech market is wild right now and we all feel cooked some days. But if AI is taking over the world, I am not going down without building the craziest open-source tools I possibly can. Go open Drawva, draw the ugliest, most crooked scribble you can think of, and watch the AI turn it into art. Aslo also also don't forget to share you crazyy dravs to the comminuty page we have one our community page And if it crashes, roast me in the GitHub issues or open a PR. And if this gave you even 1% of your developer spark back, smash a star on the repo. Let us reclaim our builder aura :