Shelf
Keep AI-built tools alive and launch them, share with agents
What it does
Shelf is a free, open-source macOS app for people who build with AI. Drop a project folder — Shelf figures out how it runs, remembers it, and launches it in one click. Connect Claude, Cursor, or Codex and they can see the same library over MCP: find a tool, launch it, check logs. New in 1.0: design profiles so agents build with your branding without you pasting hex codes. Local-first. No account. MIT.
One local library for every tool you ship. Launch them in a click, share them with a coworker in two, and serve them to your agents with your brand. No cloud. No account.
Apps and tools made with AI don’t come with a place to live. Shelf is that place. They launch in a click, and your AI tools can reach them. Hover a tool. One click and it’s running. Today, next week, two clients from now. Drop the project folder onto Shelf. It figures out how the thing runs, installs what’s missing, starts it. No terminal. No config files. No “what’s a port?” Anything your AI tool built: a Next.js site, a Python script, a Docker stack. Shelf finds the launch command, installs the packages, moves the port when it’s busy, and remembers all of it. One click to launch, today and next month. Your AI tools can find it too. The real macOS app. The library, the gaps, the sharing,…from shelfmcp.com
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 · 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