DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have your AI put a plan on a glass board with Barehands

Your AI assistant pins a plan or answer as a large card on your screen instead of only typing it.

Who it is forA solo builder or manager working with an AI assistant who wants to see plans and results visually while talking through them.

The problemLong answers in a chat window are hard to scan, and a plan typed as text is easy to lose track of while you are moving around.

The outcomeA presented card appears center stage, enlarged and spotlit, and your assistant can read back what is on the board before it speaks.

What you need first

  • A webcam
  • Google Chrome
  • Python 3 (on Windows, run.bat finds a working interpreter)
  • An internet connection on first run, because the page loads MediaPipe and three.js from CDNs

Steps

  1. Run git clone https://github.com/jaredrhod/barehands and then cd barehands.
  2. Start the app with python3 server.py (on Windows, run run.bat instead).
  3. Open http://127.0.0.1:8794/stage.html in Chrome, allow the camera, and wave.
  4. Have your assistant send a card with bin/board.sh '{"a":"present","title":"THE PLAN","body":"..."}'.
  5. Check what is on the board with bin/board-state.sh.

Prompt for your agent

In the barehands repo at <path>, run bin/board.sh with a present action that titles a card with <plan title> and puts <plan text> in the body. Then run bin/board-state.sh and confirm the card title appears in the output.

Caveat. The README says the server enforces an action allowlist and a media jail, so only the listed actions and files inside media/ will work on the board.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page