Babelize
Ship your React app in every language
What it does
Babelize automates internationalization for React apps — without the usual JSON chaos and refactors. It detects strings, generates translations with AI, and keeps everything synced as your product evolves. Built for indie developers and early-stage startups who want to ship globally from day one — not “add localization later.” No manual extraction. No messy translation files. No painful rewrites. Just build. Babelize handles the rest.
Does the same job
all alternatives →- LRLocalize React apps without rewriting code2025 · github.com · ▲89
Hi HN! We've just released an open-source React bundler plugin that makes apps multilingual—at build time, without modifying the code. React app localization typically requires implementing i18n frameworks, extracting text to JSON files, and wrapping components in translation tags - essentially rewriting your entire codebase before you can even start translating. Our React bundler plugin eliminates this friction entirely. You add it to an existing React app, specify which languages you want, and it automatically makes your app multilingual without touching a single line of your component…
- OAOne – A new React framework unifying web, native and local-first2024 · onestack.dev · ▲506
Hey HN, I'm Nate, the creator of Tamagui. One is a React framework that does two things differently in hopes of simplifying how we build websites and apps: 1. It unifies React Native and React web with typed file system routing by making Vite able to serve RN. This lets you share (or diverge) your code in a simpler way for cross-platform apps. 2. We've partnered with Zero (https://zerosync.dev) to make local-first work well. We've been building a solution in One that makes Zero supporting server rendering, without waterfalls, and with seamless server/client handoff. ---…
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
