Skip to content

OpenPipe Agent Reinforcement Trainer Train LLMs to do anything

active 2025-04-102026-07-29 (UTC)

Partial coverage11,373 / 12,270 hourly files (93%) · 2 absent upstream · 895 failed, retryable2025-03-172026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
8.2K
Pushes
1.5K
Pull requests
443
Issues
126
Stars
4.7K
Forks
383

Activity over time

Daily event counts in the loaded window

Line chart, 476 days from 2025-04-10 to 2026-07-29. Pushes: 1,497 total, peak 32 in a day. Pull requests: 443 total, peak 13 in a day. Issues: 126 total, peak 21 in a day. Comments: 289 total, peak 14 in a day. Stars: 4,733 total, peak 254 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
bradhilton7505659937
arcticfly72541615268
corbt3111346853
Kovbo2061392027
saum78008954276
vivekkalyan8059154
FurtherAI514361
angkywilliam4222611
JonesAndrew3515105
giladfrid00912015
github-actions[bot]9090
ansh-info6020
Danau5tin5002
wm199994000
Aranxtonel4003
ninehills4003
linkailong555-del4002
ExpressGradient4001
austinmw4003
jnash103003

Recent activity

Latest issues, pull requests and releases

  • Pull request#783FurtherAI2026-07-29 04:07
  • Pull request#756bradhilton2026-07-16 00:11
  • Pull request#728FurtherAI2026-06-15 22:50
  • Pull request#723FurtherAI2026-06-06 06:49
  • Issue#650Kovbo2026-06-04 00:58
    huh
  • Issue#696Kovbo2026-06-04 00:36
    ART 0.5.17 dependency Issue
  • Issue#697Kovbo2026-06-04 00:17
    Deprecated vLLM parameters in V1 engine
  • Pull request#710Kovbo2026-06-03 23:28
  • Pull request#699Kovbo2026-05-30 01:43
  • Pull request#700hardik-vala2026-05-29 00:08
  • Pull request#698Kovbo2026-05-28 00:36
  • Pull request#674FurtherAI2026-05-16 15:47
  • Issue comment#679Vinzz23032026-05-16 10:23
    examples: add local ART-E email search task
  • Issue comment#675poofeth2026-05-11 09:53
    Add local ART-E email agent example
  • Issue comment#676poofeth2026-05-11 04:44
    Support cross-entity checkpoint forks
  • Pull request#657arcticfly2026-05-07 05:38
  • Pull request#665Kovbo2026-04-29 00:26
  • Pull request#658arcticfly2026-04-23 23:32
  • Issue#656arcticfly2026-04-22 00:17
    PipelineTrainer + LocalBackend dedicated mode hangs at training step 2
  • Pull request#637vivekkalyan2026-04-18 06:13
  • Pull request#636vivekkalyan2026-04-18 03:34
  • Pull request#635vivekkalyan2026-04-18 01:16
  • Issue comment#636vivekkalyan2026-04-14 06:14
    feat: Add dedicated merged mode to Megatron backend
  • Issue#651arcticfly2026-04-13 20:55
    LocalBackend fork_checkpoint doesn't update vLLM's initial LoRA
  • Pull request#648Kovbo2026-04-10 00:07

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 4,733 stars here means stars gained during the window, not the repo's star count.