We've built an AI agent with a dev environment that can build real apps
Hey HN, Databutton is an AI agent with a full-stack dev environment that it shares with the user, which writes, tests and deploys apps using React as the frontend and FastAPI as the backend. Today, it's a way for non-professional coders to ship real full-stack apps end-to-end. The agents are leaning on the users quite frequently to give feedback and guide the development journey through prompts, images, etc. The aspiration is to increase the "autonomy" slowly, but we're built on the philosophy that users should always be able to ship real apps that can be used, even if they have to rely on…
In plain words
Databutton is an AI agent paired with a shared development environment that helps users build, test, and deploy full-stack applications using React and FastAPI. Designed for non-professional coders, it generates code based on user prompts and images while allowing users to guide development and make edits. The system emphasizes creating real, deployable apps that can be immediately used, with plans to gradually increase the agent's autonomy over time.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, Databutton is an AI agent with a full-stack dev environment that it shares with the user, which writes, tests and deploys apps using React as the frontend and FastAPI as the backend. Today, it's a way for non-professional coders to ship real full-stack apps end-to-end. The agents are leaning on the users quite frequently to give feedback and guide the development journey through prompts, images, etc. The aspiration is to increase the "autonomy" slowly, but we're built on the philosophy that users should always be able to ship real apps that can be used, even if they have to rely on other tools and LLMs to paste into our code editor. We're mostly using gpt-4o as the underlying LLM, and we've had a few hundred people helping us test and ship apps over the past few months -- and now we're opening it up for more people to help us make it better by providing feedback and shipping awesome apps. We'll try to do more updates here on HN as we progress further, as I know there's a lot of talented ai-devs / LLM-devs and enthusiasts here and I'm sure there's plenty of stuff we can learn from y'all.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, June 2024
the whole month →
La Growth Machine▲1,216Create personalized, multi-channel conversations at scale
AI · 2024 · lagrowthmachine.com
PyjamaHR▲1,132Hiring on autopilot. The AI applicant tracking system (ATS).
Work · 2024 · pyjamahr.com