timesfm license, foundation and stars
ML frameworks · Apache 2.0 (open source) · backed by Google Research · 35,312 stars
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
License history
LICENSE fileApache 2.0 No license change recorded since the repository was created in 2024.
Latest release
No GitHub releases published; the project releases elsewhere (tags or its own site).
More in ml frameworks
| Project | Stars | |||
|---|---|---|---|---|
| Apache 2.0 | 201k | +180 | v2.21.0Mar 6, 2026 | |
| Apache 2.0 | 169k | +337 | v5.17.0Sep 9, 2026 | |
| MIT | 112k | +387 | - | |
| BSD-style | 105k | +311 | v2.14.0Sep 2, 2026 | |
| Apache 2.0 | 92.2k | +333 | - | |
| Apache 2.0 | 91.4k | +77 | - | |
| Apache 2.0 | 79.2k | +407 | - | |
| Apache 2.0 | 77.4k | +122 | - |
About and history
- Repository
- google-research/timesfm · created Apr 29, 2024
- Website
- research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting
- Language
- Python
- Foundation
- None; run by Google Research
- Company
- Google Research · on Companies · on Leaders · on socials
- GitHub detects
- Apache-2.0
- Stars per week
- 274 (GitHub weekly snapshots)
Weekly snapshots
| Week of | Stars | |
|---|---|---|
| Nov 2, 2026 | 35,312 | |
| Oct 26, 2026 | 34,817 | |
| Oct 12, 2026 | 34,589 | |
| Oct 5, 2026 | 34,168 | |
| Sep 21, 2026 | 33,671 |