ManualMode
Coding fitness for engineers who ship with AI agents
What it does
ManualMode turns AI-heavy development into adaptive manual practice. Connect your coding agent and it reserves one useful task from your repositories for you to complete yourself. When project work does not fit, short browser reps target code reading, debugging, test design, async reasoning, and AI review. Start free with three Gym reps and one Project rep. Pro adds an ongoing adaptive queue.
ManualMode reserves useful manual tasks from your repositories and adds tailored browser drills for AI-heavy engineers.
Connect your coding agent. ManualMode reserves useful tasks from your own repositories for you to complete manually. Tailored Gym reps fill the gaps when real work does not fit. Selected from your repository because async reasoning is under-trained. 1 async function search(query) { 2 const request = ++latestRequest; 3 const response = await api.search(query); 4 setResults(response.items); 5 } Newest request wins No course catalog. No task hunting. ManualMode picks the work and learns from what you prove. Three Gym reps calibrate your starting point; one Project rep proves the workflow. Reserve useful project work first. Use Gym when no right-sized task fits. ManualMode gives your coding…from manualmode.dev
Does the same job
all alternatives →
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 · 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 · 17d ago · simedw.com