Skip to content

OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation

active 2025-04-132025-09-29 (UTC)

Complete coverage26,456 / 26,456 hourly files (100%) · 2 absent upstream2023-08-152026-08-21 (UTC)
Events
332
Pushes
55
Pull requests
0
Issues
20
Stars
223
Forks
7

Activity over time

Daily event counts in the loaded window

Line chart, 170 days from 2025-04-13 to 2025-09-29. Pushes: 55 total, peak 11 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 20 total, peak 3 in a day. Comments: 24 total, peak 5 in a day. Stars: 223 total, peak 57 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
OpenHelix-robot514404
Cuixxx2510010
tigernie211-git5001
X7J924001
mcddddz3002
dstx1233001
lilin962001
NielsRogge2001
BaiShuanghao1100
10270393121001
SophiaLcy1001
caichuang04151001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#12Cuixxx2025-09-26 19:27
    Any problem about the traning and evaluation code of OpenHelix
  • Issue comment#12SophiaLcy2025-09-25 14:38
    Any problem about the traning and evaluation code of OpenHelix
  • Issue#15tigernie211-git2025-09-25 08:53
    The rot loss does not decrease.
  • Issue#15tigernie211-git2025-09-24 08:38
    The rot loss does no decrease.
  • Issue comment#14Cuixxx2025-09-05 15:27
    the text encoder for system1 actually uses LLVA, not CLIP's text encoder.
  • Issue comment#14tigernie211-git2025-09-05 07:06
    the text encoder for system1 actually uses LLVA, not CLIP's text encoder.
  • Issue#13Cuixxx2025-09-04 16:02
    Could you provide a loss convergence curve?
  • Issue comment#14Cuixxx2025-09-04 16:02
    the text encoder for system1 actually uses LLVA, not CLIP's text encoder.
  • Issue#14tigernie211-git2025-09-04 07:39
    the text encoder for system1 actually uses LLVA, not CLIP's text encoder.
  • Issue comment#12Cuixxx2025-09-01 18:55
    Any problem about the traning and evaluation code of OpenHelix
  • Issue comment#13X7J922025-09-01 01:53
    Could you provide a loss convergence curve?
  • Issue#8Cuixxx2025-08-31 18:46
    Package problem about pycocotools
  • Issue comment#13Cuixxx2025-08-31 18:45
    Could you provide a loss convergence curve?
  • Issue#7Cuixxx2025-08-22 01:04
    OpenHelix evaluation doesn't work
  • Issue#10Cuixxx2025-08-22 00:53
    conflicts between the CALVIN and OpenHelix environments
  • Issue comment#8mcddddz2025-08-21 07:17
    Package problem about pycocotools
  • Issue comment#10Cuixxx2025-08-21 03:49
    conflicts between the CALVIN and OpenHelix environments
  • Issue comment#8Cuixxx2025-08-21 03:46
    Package problem about pycocotools
  • Issue comment#6Cuixxx2025-08-21 03:35
    Where is '/3d_diffuser_actor/train_logs/diffuser_actor_calvin_nohistory.pth' ?
  • Issue comment#7Cuixxx2025-08-21 03:29
    OpenHelix evaluation doesn't work
  • Issue comment#1110270393122025-08-20 07:28
    Planned Release of RLbench Experiment Results
  • Issue#11X7J922025-08-19 12:08
    Planned Release of RLbench Experiment Results
  • Issue#9X7J922025-08-19 12:04
    IndexError: index 0 is out of bounds for dimension 0 with size 0
  • Issue#10tigernie211-git2025-08-19 09:03
    conflicts between the CALVIN and OpenHelix environments
  • Issue comment#7mcddddz2025-08-18 02:41
    OpenHelix evaluation doesn't work

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 223 stars here means stars gained during the window, not the repo's star count.