aralroca

aralroca

AI agents shouldn't control your apps; they should BE the app

I wrote about a different approach to AI agents. Instead of building bots that screenshot your screen and click buttons (like OpenAI Operator or Anthropic Computer Use), I built 304 browser tools where the AI agent IS the app; calling local functions directly instead of navigating UIs.
Everything runs client-side: JavaScript for simple tasks, Rust compiled to WASM for heavy computation, and ONNX/TensorFlow.js models for AI features like background removal.

Full article:

https://kitmul.com/en/blog/building-kitmul-ai-tools-os

Curious what you all think; is the “AI controlling existing apps” approach fundamentally flawed, or am I missing something?

Where Next?

Popular Ai topics Top

RobertRichards
In the early days, online gaming was limited to the screens of smartphones, PCs, tablets, and other devices. However, with the advent of ...
New
masterhood13
[Project Update] Part 2 of My Dota 2 Match Outcome Predictor – Now Available! Hey DevTalk community! I just published the second part o...
New
ozornin
I recently wrote an essay on effects of AI, how it all can become real bad, and how we can avoid it. I started writing the post intend...
New
waseigo
Top-tier LLMs, Rust and Erlang NIFs; nifty, and night and day vs. C, but let me tell you about vibe coding… After I submitted my blog po...
New
John-BoothIQ
TL;DR: Good: AI is great at Elixir. It gets better as your codebase grows. Bad: It defaults to defensive, imperative code. You need...
New
xiji2646-netizen
Anthropic announced Claude Mythos Preview this week – and then said it will not release it to the public. Their reasoning: the model’s cy...
New
wolf4earth
The structural argument, briefly: literacy installs a cognitive substrate in human brains; LLMs are built entirely on the same kind of su...
New
xiji2646-netizen
I have been looking through Seedance 2.0 prompt examples and noticed a pattern: The prompts that work best are usually not just longer. ...
New
alvinkatojr
Found this article a refreshing take on this obsession with AI tokens and “tokenmaxing”. Read and enjoy! :slight_smile:
New
T0ha666
An automated trigger fired every two minutes for 8 hours. 243 agent runs. 31M tokens. $63 wasted. The problem: nobody noticed until morni...
New

Other popular topics Top

Exadra37
I am thinking in building or buy a desktop computer for programing, both professionally and on my free time, and my choice of OS is Linux...
New
Rainer
My first contact with Erlang was about 2 years ago when I used RabbitMQ, which is written in Erlang, for my job. This made me curious and...
New
New
AstonJ
This looks like a stunning keycap set :orange_heart: A LEGENDARY KEYBOARD LIVES ON When you bought an Apple Macintosh computer in the e...
New
AstonJ
In case anyone else is wondering why Ruby 3 doesn’t show when you do asdf list-all ruby :man_facepalming: do this first: asdf plugin-upd...
New
PragmaticBookshelf
Author Spotlight Mike Riley @mriley This month, we turn the spotlight on Mike Riley, author of Portable Python Projects. Mike’s book ...
New
New
AstonJ
This is a very quick guide, you just need to: Download LM Studio: https://lmstudio.ai/ Click on search Type DeepSeek, then select the o...
New
RobertRichards
Hair Salon Games for Girls Fun Girls Hair Saloon game is mainly developed for kids. This game allows users to select virtual avatars to ...
New
xiji2646-netizen
There’s a GitHub repo at forrestchang/andrej-karpathy-skills that’s sitting at 97.8k stars. It’s a single CLAUDE.md file with four behavi...
New