Open-source benchmark for browser AI agents on daily tasks.
active 2026-04-11 → 2026-08-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 129 days from 2026-04-11 to 2026-08-17. Pushes: 66 total, peak 23 in a day. Pull requests: 3 total, peak 1 in a day. Issues: 5 total, peak 2 in a day. Comments: 2 total, peak 1 in a day. Stars: 7 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Recent activity
Latest issues, pull requests and releases
- Issue comment#264Perry20042026-08-14 04:55docs(site): keep llms.txt synchronized with live benchmark data
- Issue#248Perry20042026-07-03 18:24Validate models.yaml against model.schema.json at load (fail fast on bad entries)
- Pull request#228Perry20042026-06-13 05:28
- Issue#223Perry20042026-06-06 00:23FEAT: integrate ClawBench into Harbor framework
- Issue#211Perry20042026-05-24 01:59FIX: multi-harness support for token cost
- Pull request#212Perry20042026-05-24 01:59
- Issue#209Perry20042026-05-23 20:56REFACTOR: enhance mutli-harness structural support
- Issue#209Perry20042026-05-23 20:56REFACTOR: enhance mutli-harness structural support
- Issue comment#199Perry20042026-05-23 02:06[Question] Recommended model × harness pairings — guidance for new users?
- Pull request#203Perry20042026-05-23 01:49
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 7 stars here means stars gained during the window, not the repo's star count.