RegularMonk
Stop doom-scrolling with 4 daily mindful pauses.
What it does
RegularMonk helps you stop doom-scrolling with four short mindful pauses a day. Each pause takes under five minutes and uses a mindful game, breathing exercise, attention task, or reflection prompt to interrupt the moment of impulse. Unlike most wellness apps, there’s no feed, no streak pressure, no endless content, and pauses are time-gated so you can’t binge them. Open it, pause, leave the screen.
Does the same job
all alternatives →
- AIAn intentionally annoying app to break doomscrolling2025 · speedbumpapp.com · ▲14
Based on personal struggles, I built an app that shows annoying things on my phone when I doomscroll. This includes dancing cats, the screen time police, or rain. Social media is great as long as you don't overuse it -- I learn and connect with friends thanks to it. But it's too easy to get hooked. When you open addictive apps, SpeedBump gives you a few options: 2, 5, 15, 30 minutes. The more you want to use, the more you have to wait before opening. Once time's up, it starts to annoy you a lot. There's no way to extend the timer without breaking your streak; you'll have to take a 15 min…
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, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com