BitsExplorer

BitsExplorer finds what people are building with AI, every day. See today's picks →

Preview of Edgebench Swe

Edgebench Swe

Long-horizon coding agent benchmark built from real open-source version upgrades: 115 tasks, 17 repositories, 5 languages, weighted subtask scoring. Three complete Harbor tasks published.

Description excerpted from the original listing, which is linked below.

Open it Source code

The week in AI-built software

Every Monday: how many projects were built with AI that week, which tools built them, where they came from, and the week's picks.

Read the latest week