Urgent.News

What's breaking now, across thousands of outlets.

AI

What people are building with Jev: a look through nine awesome lists

I went looking for what people had built with Jev. Browser demos were easy to find. So were lists of lists. Getting a sense of the rest took more work. I collected the repository links from nine Jev directory READMEs. After removing repeated URLs and other directory listings, I had 1,186 different repository addresses . That isn't a count of finished apps. It includes experiments, libraries,…

Jev is a tool that divides tasks for AI assistants. For instance, deciding which emails need attention involves Jev choosing whether a message requires a reply. The assistant then writes the notification using a language model. Jev handles the decision-making process, while the AI handles the actual work. A total of 1,186 different repositories were identified across nine Jev directory READMEs.

However, not all projects are equal, with only 757 repositories appearing in a single list. There were three repositories that appeared in all nine directories. When examining the categories, the bulk of projects related to existing tools and frameworks around Jev, accounting for 25.1% of the entries. Assigning work and managing an assistant's history came next, making up 20.1% of the projects. Browser and computer control accounted for a smaller portion at 7.5%.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

GLM-5.3-Flash Explained: The 320B Open-Weight Model With an 18B Brain and a 1M-Token Memory (2026)

Verdict: GLM-5.3-Flash is the most interesting open-weight release of August 2026 not because it wins every benchmark — it doesn't — but because it reaches a near-frontier level of coding and agentic…

  • GLM-5.3-Flash is a 320 billion parameter open-weight model from Z.ai
  • Activates only 18 billion parameters per token for efficient computing
  • First natively multimodal model in Z.ai's GLM-5 series

More from Monday 21 September →