myGeeKy reads your CV, your repos and your ORCID & Google Scholar papers, then shows you the people, projects, papers and pulse of your field, in one small glass panel on the edge of your screen. It only suggests. It never acts for you.
pip install mygeekyFree and open source (MIT) · v0.15.1 · Windows installer, or pip on Windows, Linux and macOS
Your CV, repos, ORCID/OpenAlex and Google Scholar papers power everything, so it's matched to your research, not a generic popularity list.
Researchers who share your work and are likely to follow you back, plus domain experts who rarely follow anyone. Celebrities, mass-followers and dormant accounts are skipped.
Starter issues, and maintainers who merge outside PRs.
Your field's repos as a daily stock race.
Papers gaining citations fastest, and the code behind them.
arXiv, bioRxiv and Hacker News about your topics.
Every click, follow, star and fork tunes every list, and 🔭 20% always stays open for new territory, so you never end up in a bubble.
Thank someone, say you learned from their work or used their tool. Sealed so only they can read it, and no reply is ever expected. 🤝 "Let's collaborate" only shows up if you both choose it.
What your people are building, live.
Sync through a private repo you own.
Always on top, in three glass themes. Click a tab, or just watch.
From OpenAlex, matched to your own research topics.

Fresh items from arXiv, bioRxiv and Hacker News, kept only when they genuinely match your interests: two of your terms, or one exact phrase.

The Model tab draws it as a living map: you in the middle, your research field around you, what you've been into lately pulsing further out, and today's new territory on the edge.
Add "AI" and myGeeKy also looks for LLMs, deep learning and AI agents. Add "GWAS" and it brings in genomics and statistical genetics. A small model learns what goes together from GitHub's open data.
Keywords in the dictionary bring their whole meaning to People, Repos, Research and News, each related idea weighted by how closely it goes with yours.
Your own words still work, as plain words. They're passed on, through your beacon or with one click, so the next dictionary learns them.
A new dictionary reaches everyone by itself, at most once a week. No server, nothing hidden: the model is a few hundred lines you can read.
A quiet way to tell someone their work mattered to you: no server, no text, nothing to moderate, and nothing to answer.

From a fresh Windows PC to your first suggestions.
There is no follow, star or fork code in myGeeKy at all. And it uses two GitHub tokens with very different powers. Setup checks what each can actually do, and refuses one that doesn't fit its job.
mygeeky-beacon repo, and nothing else.mygeeky-beaconTokens live in your OS keyring (Credential Locker, Keychain, Secret Service), never in a file, never logged.
No server, no account, no telemetry. Sync, if you want it, goes to a private GitHub repo you own.
MIT-licensed and on GitHub, with tests. Read exactly what it does, and change it if you like.
On Windows, run the installer: Next → Next → Finish. It sets up Python and Git if you don't have them. Anywhere else:
pip install mygeeky
Your GitHub username, plus your CV, ORCID or Scholar profile if you like, and token 1.
mygeeky init
Everything, live. The first run sets up the GUI by itself.
mygeeky gui
Click 💡 in the panel. Your browser opens a ready-to-send issue in myGeeKy-ideas, and you press Submit. Nothing is sent until you do.
Free, open source, and yours.
The installer isn't code-signed yet. If Windows warns you, click More info → Run anyway.