I built an open-source AI app builder you can watch think — looking for contributors

A developer has released Devgri AI, an open-source, MIT-licensed AI app builder that generates applications from plain-language descriptions and displays the result across three synchronized panes: a chat interface, an editable architecture-tree node graph, and a live preview. The tool is bring-your-own-key, keeping Anthropic, OpenAI or Google credentials in browser memory with client-side PII and token masking, and enforces usage rules such as trial windows and user caps through row-level security policies rather than the UI alone. The project is an early MVP and its author is soliciting contributors, issues and pull requests.

Most AI app builders give you a chat box and hand back a wall of code. You can't see how the app is structured until you dig through it. So I built Devgri AI https://github.com/Sumontsc51/Devgri-ai — you describe an app in plain language and get three panes that stay in sync: | Pane | What it does | |---|---| | Chat | Describe what you want, in plain language | | Architecture tree | The app's structure as an editable node graph — drag, rename, reconnect | | Live preview | The generated site renders beside the tree as it changes | 👉 Live demo: https://devgri-ai-olive.vercel.app https://devgri-ai-olive.vercel.app 👉 Repo: https://github.com/Sumontsc51/Devgri-ai https://github.com/Sumontsc51/Devgri-ai Devgri is BYOK — your Anthropic, OpenAI or Google key stays in browser memory. PII and token masking runs client-side before anything leaves the tab, and keys are stripped from every payload before a workspace is saved. One thing I like: rules like the trial window and user cap are enforced in RLS policies , not just the UI, so the API can't be talked around. It's an early MVP. It works end to end, but it's rough in places — which is exactly why it's public and MIT licensed. Contributions I'd love: The repo has a CONTRIBUTING.md https://github.com/Sumontsc51/Devgri-ai/blob/main/CONTRIBUTING.md , and getting it running locally takes a few minutes: git clone https://github.com/Sumontsc51/Devgri-ai.git cd Devgri-ai npm install cp .env.local.example .env.local fill in your Supabase values npm run dev If you try it, I'd really like to hear what breaks and whether the architecture-tree idea is useful to you. Issues, PRs and ⭐s all welcome