Skip to content

它可以根据需求描述,直接生成新材料 它可以生成具有化学、机械、电子或磁性属性的材料,或多种特性的组合Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.

Python · active 2025-01-162026-07-17 (UTC)

Complete coverage26,593 / 26,593 hourly files (100%) · 2 absent upstream2023-08-152026-08-27 (UTC)
Events
2.6K
Pushes
69
Pull requests
73
Issues
223
Stars
1.5K
Forks
262

Activity over time

Daily event counts in the loaded window

Line chart, 548 days from 2025-01-16 to 2026-07-17. Pushes: 69 total, peak 9 in a day. Pull requests: 73 total, peak 6 in a day. Issues: 223 total, peak 9 in a day. Comments: 352 total, peak 15 in a day. Stars: 1,497 total, peak 288 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

Recent activity

Latest issues, pull requests and releases

  • Issue comment#233danielzuegner2026-02-27 17:18
    How to get energy_above_hull_per_atom for every crystal
  • Pull request#239danielzuegner2026-02-27 16:45
  • Issue comment#234danielzuegner2026-02-27 16:16
    Specify the number of atoms for generations
  • Pull request#237ClaudioZeni2026-02-20 18:44
  • Issue comment#195hfzxlzy2026-02-06 04:49
    Numpy <2 requirements conflicts with mattersim
  • Issue#235SE-Wd2026-02-02 16:05
    Issues with Baseline Model Evaluation
  • Issue comment#229danielzuegner2026-01-05 15:46
    Bugs for evaluating the novelty, stability and uniqueness of generated structures
  • Issue#221danielzuegner2026-01-05 15:46
    OSError: [WinError 127] 找不到指定的程序。
  • Issue comment#228rongaoli2025-11-24 06:01
    Return MAX_RMSD instead of MAX_RMSD/norm when no match found
  • Issue comment#223Pepe-Marquez2025-11-12 10:35
    TypeError: Optimizer.converged() missing 1 required positional argument: 'gradient'
  • Issue comment#221danielzuegner2025-11-10 15:57
    OSError: [WinError 127] 找不到指定的程序。
  • Issue#217danielzuegner2025-11-10 08:51
    MisconfigurationException('No supported gpu backend found!')
  • Issue comment#224danielzuegner2025-11-10 08:48
    Issues in unconditional generation using chemical_systems pretrained model
  • Issue comment#224cypherumang652025-11-05 11:13
    Issues in unconditional generation using chemical_systems pretrained model
  • Issue#224cypherumang652025-11-03 04:11
    Issues in unconditional generation using chemical_systems pretrained model
  • Issue comment#223bppece2025-10-31 11:12
    TypeError: Optimizer.converged() missing 1 required positional argument: 'gradient'
  • Issue comment#222danielzuegner2025-10-28 13:35
    Generated Crystals Only Contain Element 101 (Md) Due to Missing Filtering in sample_and_compute_posterior_q
  • Issue#222Mority52025-10-24 02:25
    Generated Crystals Only Contain Element 101 (Md) Due to Missing Filtering in sample_and_compute_posterior_q
  • Issue#221aoyue2412025-10-23 13:38
    OSError: [WinError 127] 找不到指定的程序。
  • Pull request#218danielzuegner2025-10-06 12:38
  • Issue#217yl26232025-10-03 19:55
    MisconfigurationException('No supported gpu backend found!')
  • Issue#216zfahim572025-10-01 21:12
    Evaluation error after successful installation
  • Issue comment#213hspark12122025-09-23 08:18
    Conditional sampling for "dft_band_gap = 3 eV" yields many near-zero values
  • Issue comment#213ClaudioZeni2025-09-23 07:49
    Conditional sampling for "dft_band_gap = 3 eV" yields many near-zero values
  • Issue comment#213ClaudioZeni2025-09-22 09:42
    Conditional sampling for "dft_band_gap = 3 eV" yields many near-zero values

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,497 stars here means stars gained during the window, not the repo's star count.