Moinaki — ADHD-friendly learning
Learning for brains that don't finish online courses
What it does
Most learning apps weren't built for ADHD brains. Streaks shame you. Long lessons lose you. Mentors forget you between sessions. moinaki is different. 5-minute lessons. An AI mentor with long-term memory that picks up exactly where you left off. A skill map that grows with you. Skip what you already know. No streaks. No guilt. Just learning that fits how your brain actually works.
Does the same job
all alternatives →
- IBI built a free tool for breaking down tasks into manageable subtasks2024 · voxtodo.com · ▲48
Hi HN! First time posting. I created a tool for my Autistic son who is in high school junior battling severe ADHD symptoms. His difficulties include; 1. Time blindness 2. Lack of executive functioning skills 3. Task initiation issues These three were severely affecting his grades. We had a consultation with a Developmental Psychologist who prescribed Concerta that improves his ability to focus in class. In addition he also has the boilerplate ADHD accommodations(2X time on tests and quiet place to take the test). These collectively improved his test taking abilities. But, when it came to his…
- IMI made a tool that uses AI to turn my ADHD brain into a super power2025 · scatternote.com · ▲8
I really struggle to keep my notes organised, and often can't make any sense of hand written notes after meetings. I did some experiments with Claude and ChatGPT where I blast random thoughts at them during a meeting or brainstorming session and then have them output a nice document that pulls it all together at the end. It worked incredibly well but it was a bit cumbersome to keep sending messages to the chat and telling the ai each time what to do. So I took the idea and built a tool, it makes it easy to throw random notes and voice recordings (images and document support on the way) and…
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