Activity
Stars and mentions · Last 30 days, Oct 19 – Nov 17
Top repositories
enapt’s repositories ranked by new forks, as on trending.
Contributes to
Repositories outside enapt’s account where enapt opened or reviewed pull requests in the past 365 days.
Who noticed enapt
Everyone who starred or forked enapt’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories enapt owns. Select an award to embed its badge.
No awards yet
Repositories earn awards by reaching the top three in a completed trending day or week.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
SwarmLLM: Free, open-source app that lets computers team up over the internet to run models too big for one machine. “Run AI on your own computer. Run bigger AI together. SwarmLLM is a free app that gives you a ChatGPT-style assistant running on your own computer, using open AI models from Meta, Google, Alibaba, Mistral and others. When a model is too big for one machine, computers running SwarmLLM team up over the internet and run it together, each doing part of the work. No account · No subscription · No ads · No crypto · Open source · Updates itself A giant model has now run on the swarm. Bigger AI models give noticeably smarter answers, but the biggest open ones (70 billion "parameters" and up) need equipment normally found only in data centres — no home computer can hold one. In October 2026, Llama 3.3 70B answered across four ordinary computers in Thailand, Australia and Italy, each holding a part of it. It is slow so far” The decentralised concept of this is promising, even if it’s currently too slow to be a sensible way to run large models.