Skip to content

Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.

Python · active 2025-08-28 → 2026-03-05 (UTC)

Complete coverage27,325 / 27,325 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-09-26 (UTC)
Events
143
Pushes
11
Pull requests
0
Issues
2
Stars
113
Forks
12

Activity over time

Daily event counts in the loaded window

Line chart, 190 days from 2025-08-28 to 2026-03-05. Pushes: 11 total, peak 4 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 2 total, peak 1 in a day. Comments: 4 total, peak 3 in a day. Stars: 113 total, peak 19 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.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 113 stars here means stars gained during the window, not the repo's star count.