Happy Coder – End-to-End Encrypted Mobile Client for Claude Code
Hey all! Few weeks ago we realized AI models are now so good you don't need to babysit them anymore. You can kick off a coding task at lunch and Claude Code just... works. But then you're stuck at your desk steering it. We were joking around - wouldn't it be cool to grab coffee and keep chatting with Claude from your phone? Next thing you know, 4 of us are hacking on weekends to make it happen. Dead simple to try: "npm install -g happy-coder" then run "happy" instead of "claude". That's it. We had three goals: * Don't break anyone's flow - Use Claude Code normally at your desk, pick up your…
In plain words
Happy Coder is a mobile client that lets developers continue Claude Code conversations on their phone while away from their desk. Installation is straightforward via npm, and it uses end-to-end encryption so the service cannot access user data. The tool is designed to maintain the existing Claude Code workflow without interruption, allowing developers to check on coding tasks or provide guidance remotely without being tethered to their computer.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey all! Few weeks ago we realized AI models are now so good you don't need to babysit them anymore. You can kick off a coding task at lunch and Claude Code just... works. But then you're stuck at your desk steering it. We were joking around - wouldn't it be cool to grab coffee and keep chatting with Claude from your phone? Next thing you know, 4 of us are hacking on weekends to make it happen. Dead simple to try: "npm install -g happy-coder" then run "happy" instead of "claude". That's it. We had three goals: * Don't break anyone's flow - Use Claude Code normally at your desk, pick up your phone when you leave. Nothing changes, nothing breaks. * Actually private - Full E2E encryption, no regular accounts. Your encryption keys are created on your phone and securely paired with your terminal. We protect our infra, not your data (because we literally can't see it). * Hands-free is the future - This was the fun one. We hooked up 11Labs' new realtime SDK so you can literally talk to Claude Code through GPT-4.1 while walking around. Picked 11Labs because we can configure it to not store audio or transcripts. The mobile experience turned out pretty great - fast chat, works on everything (iPads, foldables, whatever), and there's a web version too. It's free! The app and chat are completely free. Down the road we'll probably charge for voice inference or let you run it client-side with your own API keys. Links to apps iOS: https://apps.apple.com/us/app/happy-claude-code-client/id674... Android (just released): https://play.google.com/store/apps/details?id=com.ex3ndr.hap... Web: https://app.happy.engineering Would love to hear what you think!
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 · 26d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca