PyPI Stats
pytorch

captum

Model interpretability and understanding for PyTorch
PyPI GitHub
Downloads
Day
20.8K
Week
99.3K
Month
482.3K
Stars
5.6K
Forks
557
Issues
224
Version
0.9.0

Package Insights

What's this?
Score breakdown - each component scores 0–100, weighted by percentage
Maintenance
90
Popularity
79
Adoption
56
Community
70
How the maintenance status was determined
Last commit
5 days ago
Monthly downloads
482,287
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
482,287
Stars
5,622
Stars per 1k downloads
11.66
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
• Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
14,191
Month daily avg
16,076
Momentum
-11.7%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
Python version support tiers
requires_python
>=3.10
Cutting Edge
Minimum supported version is 3.12 or newer
• Modern
Minimum supported version is 3.9, 3.10, or 3.11
Legacy
Supports 3.8 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
BSD-3-Clause
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
19 days ago
Total releases
12
Releases/year
1.8
Rapid
Last release within 365 days and > 12 releases/year
• Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
133
Monthly downloads
482,287
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
64
 
Issue Burden
39.8
per 1k stars
Discussions
0.0
per 1k stars
Fork Ratio
23.9%
contrib / forks
Stale Release
No
 
PR Velocity
Quiet
 

Weekly Downloads

GitHub Stars

Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

Linux 6.3K
Windows 192
macOS 78

Python Versions

3.12
56.9% 3.5K
3.11
22.5% 1.4K
3.10
12.4% 762
3.13
4.5% 277
3.9
3.7% 230

Top Countries

1. US US
3.8K
2. DE DE
1.1K
3. KR KR
374
4. SG SG
274
5. IE IE
205
6. NL NL
192
7. CA CA
132
8. IN IN
64
9. CN CN
41
10. DK DK
39

Package Information

License
BSD-3-Clause
First Release
September 3, 2019
Last Release
2 weeks ago
Last Commit
5 days ago
Latest Version
0.9.0
Total Releases
12
Contributors
133
Open PRs
33
Archived
No
Author
PyTorch Team
Wheels
py3
Keywords
Model Interpretability Model Understanding Feature Importance Neuron Importance Data Attribution Explainable AI PyTorch
Topics
interpretability interpretable-ai interpretable-ml feature-importance feature-attribution
Tracking Since
January 6, 2026
Data Updated
May 3, 2026
Data Freshness
Fresh

Links