HaruBrief
AI calendar copilot that spots burnout before you do
What it does
HaruBrief reads your calendar so you don't have to. Get a one-sentence daily summary with an energy score from 0 to 100. It counts meetings, finds free time, and flags lunch overlaps. If your week looks packed, it sends a burnout risk alert based on meeting density, overtime, and weekend intrusions. Works with Google Calendar, iCloud, Outlook, and Exchange. No manual input. Just connect your calendar. Built for the worker who showed up Monday to 11 back-to-back meetings and zero lunch breaks.
Does the same job
all alternatives →
Lifestack (Web + AI Scheduler)2025 · ▲576First AI calendar to use health data for better productivity
- IBI built a task manager that separates "do" and "due" dates2024 · apps.apple.com · ▲160
Hi HN, I’m the founder of Zesfy, a productivity app that I’ve been developing over the past few years. It’s designed to seamlessly integrate your tasks with your calendar, allowing you to transform your to-do lists into actionable events in just seconds. Here are some of its key features: - Task Progress: Automatically update your progress based on subtasks completed - Step: Create step-by-step breakdown of the subtask - Target: Organize tasks with due date - Session: Insert multiple tasks to calendar event - Space: Filter event from specific sets of calendars I recently introduced new…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
