
PureStrength
Improve your compound lifts
What it does
Upload your Squat, Bench or Deadlift and get detailed bar path analysis (velocity, ROM, side shift and pause time) and form feedback (squat depth and deadlift spinal curvature). 1 rep max calculation from warm up sets and a velocity zone based program.
Does a similar job
all alternatives →

- SLStrength Level – Squat/Deadlift/Bench Calculator2015 · strengthlevel.com · ▲12
- LWLiftosaur – Weightlifting tracker app for coders2023 · liftosaur.com · ▲26
I made a weightlifting tracker app specifically for coders. In weightlifting, progressive overload is one of the most important parts of gaining muscle. You should constantly increase weights, reps, use different set schemes, and that will make your muscles grow. There're many weightlifting programs, using various overloading schemes - linear increasing of weights, some periodic ladder-up increase, switching to different set schemes in case of failures, etc. You can implement all of that in Liftosaur. It works this way: each exercise may define a bunch of variables, that could be changed…

- MBMaxx Bench – Gravity Release Bench Press2015 · kickstarter.com · ▲11
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 · 19d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 21d 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 · 29d ago · cactuscompute.com


Source: Product Hunt launch ↗