Skip to content

Evaluate and improve AI agents from the data they produce.

active 2026-04-202026-08-11 (UTC)

Partial coverage12,646 / 14,378 hourly files (88%) · 2 absent upstream · 1,726 failed, retryable2024-12-202026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
557
Pushes
275
Pull requests
29
Issues
2
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 114 days from 2026-04-20 to 2026-08-11. Pushes: 275 total, peak 12 in a day. Pull requests: 29 total, peak 4 in a day. Issues: 2 total, peak 1 in a day. Comments: 9 total, peak 2 in a day. Stars: 0 total, peak 0 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

ContributorContributionsPushesPRsComments
drewstone247221200
tangletools805299
shekohex1100
AtelyPham1100

Recent activity

Latest issues, pull requests and releases

  • Pull request#571drewstone2026-08-11 00:30
  • Issue#544drewstone2026-08-04 04:16
    fix(cost): bound CLI-backed model overhead without false reservations
  • Issue comment#509tangletools2026-07-31 21:48
    chore(ci): delete scheduled paid optimizer benchmark workflow
  • Issue comment#501tangletools2026-07-31 06:34
    feat(analyst): report incorrect steps as contiguous failure blocks
  • Issue comment#457tangletools2026-07-28 03:22
    fix(gates): promotion gates were blind to binary outcomes; decide on an exact interval and fail closed
  • Issue#386drewstone2026-07-25 18:19
    [BUG] defaultProductionGate reports green for unevaluated checks, three doc claims are false, and the safety composition cannot be configured honestly
  • Issue comment#284tangletools2026-06-27 15:49
    fix(red-team): score refusal context safely
  • Pull request#263drewstone2026-06-20 23:50
  • Issue comment#248tangletools2026-06-14 03:49
    fix(produced-state): faithful completion oracle — content-aware, ungameable, form-vocabulary-robust
  • Pull request#220drewstone2026-06-05 18:45
  • Issue comment#218tangletools2026-06-05 17:03
    feat(belief-state): build code-agent evidence corpus
  • Pull request#161drewstone2026-06-01 14:43
  • Pull request#156drewstone2026-05-31 22:50
  • Pull request#150drewstone2026-05-31 16:17
  • Pull request#146tangletools2026-05-31 01:40
  • Pull request#145tangletools2026-05-31 00:26
  • Pull request#141drewstone2026-05-30 21:19
  • Pull request#139tangletools2026-05-30 20:13
  • Pull request#136tangletools2026-05-30 16:26
  • Issue comment#133tangletools2026-05-30 15:23
    chore(release): 0.61.0 — runProfileMatrix + runCampaign token capture
  • Pull request#130tangletools2026-05-27 23:31
  • Pull request#126tangletools2026-05-27 22:51
  • Pull request#118tangletools2026-05-27 12:10
  • Pull request#101drewstone2026-05-25 19:11
  • Pull request#87tangletools2026-05-23 23:45

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.