Fitly AI
One AI agent instead of five fitness apps
What it does
Fitly AI is an AI agent that runs your whole fitness life through one conversation. Type, talk, or send a photo and it logs meals, workouts, water, and weight. Name a destination (down 20 by the wedding, a first 10K) and it writes the game plan: your meals, your training, your pace to arrival. When life throws a curveball, the plan bends, not you. It is also an open platform: an MCP server with 50+ tools lets Claude, ChatGPT, or any agent you already use read your progress and log for you.
You didn't quit fitness. You quit the tracking app. Fitly AI logs meals from a text or photo, builds your plans, and tracks your macros for you.
Fitly is an agent you text like a person. Say what you ate or snap a photo and it's handled: the logging, the plans, the macro math. Let your agent do the tracking. A meal, water, a workout, and a weigh-in from one sentence. Twenty seconds, done. If you've quit a tracking app, you already know why: the database searches, the serving-size math, the dozen taps just to log a sandwich. That wasn't a you problem. It was a homework problem. Fitly skips all of it. Say what you had and it's logged. Scan, snap, or type by hand when you want. You never have to. The modern fitness setup is a part-time job: five apps, none of them talking to each other, and you carrying the numbers in between. Fitly…from fitly.chat
Does the same job
all alternatives →
MikeAI - Personalized AI Fitness Coach2023 · ▲102Get in shape - take your fitness journey to the next level
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 · 16d 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 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com