Belay - Awake For AI Agents
Stays awake while your agents work.
What it does
Belay keeps your Mac awake while local coding agents are working, then lets it sleep when they're done. No timers to start, no caffeine switch to remember, and no account or telemetry.
A free menu bar app that keeps your Mac awake while Claude Code, Codex, Cline and Copilot work – not caffeinate, but a power layer for local AI agents on macOS.
Like what Belay does? A star on GitHub is how the next developer finds it. Belay keeps your Mac awake while a coding agent is working. When the work stops, Belay gets out of the way and your Mac can sleep normally again. Built-in detection for Claude Code, Codex, Cline and Copilot CLI, plus one-click presets for Gemini CLI, OpenCode, Aider and Pi. You can also point Belay at a folder for anything else. Detection stays on your Mac. No account. No telemetry. Belay never sends your prompts or code anywhere. Free & open code. Release notes • Roadmap • Demo Belay is free, and the code is open. If it saved you a run, a star on GitHub costs nothing and helps other people find it. Bug…from perfectoweb.github.io
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