Skip to content

Thermodynamic Hypergraphical Model Library in JAX

active 2025-10-292026-07-09 (UTC)

Partial coverage11,294 / 12,108 hourly files (93%) · 2 absent upstream · 812 failed, retryable2025-03-242026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
530
Pushes
21
Pull requests
8
Issues
8
Stars
429
Forks
10

Activity over time

Daily event counts in the loaded window

Line chart, 254 days from 2025-10-29 to 2026-07-09. Pushes: 21 total, peak 5 in a day. Pull requests: 8 total, peak 2 in a day. Issues: 8 total, peak 2 in a day. Comments: 28 total, peak 4 in a day. Stars: 429 total, peak 103 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
lockwo3418112
extropic-oss10214
visvig8004
AnthonE3012
Th0rgal3001
Sohailm253021
sugolov2001
sukrucildirr2011
dtunai1001
krishjp1000
xenn00101010
ran-weii1000
drabanus1000
asmit2031000
Space14151001
notesbymuneeb1000
sethmorton1100
NinoRisteski1000
saltzberg1010

Recent activity

Latest issues, pull requests and releases

  • Issue#42asmit2032026-05-03 06:52
    [General Query] Is there any plan to release the code in CPP
  • Issue comment#40lockwo2026-04-04 05:20
    feat: ThermoTorch — The 'CUDA' Bridge for Extropic TSUs & Probabilistic Graph Execution
  • Issue comment#35AnthonE2026-02-22 19:41
    Add Pe calibration example: fitting THRML to empirical drift data
  • Issue comment#32AnthonE2026-02-22 19:41
    Add EBM parameter fitting example (addresses #29)
  • Pull request#34AnthonE2026-02-22 03:12
  • Issue#29ran-weii2025-11-17 00:56
    Expose functions for training arbitrary EBMs
  • Issue comment#11lockwo2025-11-15 17:48
    Fix MomentAccumulatorObserver dtype handling for mixed node types
  • Issue comment#25lockwo2025-11-10 20:06
    Add full 9x9 Sudoku solver with visualization and annealing metrics
  • Issue comment#24lockwo2025-11-09 06:30
    THRML Max-Cut on Apple M2: results and question on expected TSU hardware speedup
  • Issue#24Th0rgal2025-11-08 20:31
    THRML Max-Cut on Apple M2: results and question on expected TSU hardware speedup
  • Issue#13Th0rgal2025-11-07 11:53
    A few questions about how it works
  • Issue comment#13Th0rgal2025-11-07 11:53
    A few questions about how it works
  • Issue comment#23lockwo2025-11-05 22:51
    Add Restricted Boltzmann Machine (RBM) implementation
  • Pull request#23xenn00102025-11-05 21:36
  • Issue comment#19lockwo2025-11-05 20:34
    Numpy < 2 recommended
  • Pull request#22lockwo2025-11-05 20:25
  • Issue#19drabanus2025-11-05 15:02
    Numpy < 2 recommended
  • Issue comment#11Sohailm252025-11-03 18:23
    Fix MomentAccumulatorObserver dtype handling for mixed node types
  • Pull request#17saltzberg2025-11-03 13:29
  • Issue#16notesbymuneeb2025-11-03 06:48
    `hinton_init` initialization issues with constraint penalties
  • Issue comment#15lockwo2025-11-03 02:09
    docs: update image path
  • Issue comment#16lockwo2025-11-03 02:07
    `hinton_init` initialization issues with constraint penalties
  • Issue comment#15sukrucildirr2025-11-02 13:50
    docs: update image path
  • Issue comment#1lockwo2025-10-31 06:20
    Update installation instructions to use uv instead of pip
  • Issue comment#6extropic-oss2025-10-30 21:24
    docs: Add uv installation & tests instructions to README

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 429 stars here means stars gained during the window, not the repo's star count.