google-research

    google-research/timesfm

    TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

    backend
    Python
    Apache-2.0
    35.6K stars
    3.5K forks
    224 GitHub watchers
    Updated Nov 16, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    1 release in the last 90 days, the latest 79 days ago, with 50 contributors on GitHub.

    Peaked at #11 in the weekly ranking the week of Apr 12, its best in the past year.

    Use Cases & Benefits

    • Provides a pretrained foundation model for accurate time-series forecasting using a decoder-only architecture.
    • Delivers superior forecasting accuracy with long context lengths and supports finetuning and covariate integration.
    • Use for forecasting univariate time series with high-frequency data such as daily or hourly measurements.
    • Use for incorporating static and dynamic covariates to improve forecasts in complex scenarios like retail sales prediction.
    • Use for fine-tuning the pretrained model on custom datasets to adapt forecasts to specific domains or new data.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

    This repo contains the code to load public TimesFM checkpoints and run model inference. Please visit our Hugging Face release to download model checkpoints.

    This is not an officially supported Google product.

    We recommend at least 32GB RAM to load TimesFM dependencies.

    Excerpt from the google-research/timesfm README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    05001.0KSep 3: +1,207Sep 4: +344Sep 5: +275Sep 6: +302Sep 7: +259Sep 8: +162Sep 9: +141Sep 10: +68Sep 11: +46Sep 12: +97Sep 13: +60Sep 14: +76Sep 15: +127Sep 16: +177Sep 17: +222Sep 18: +127Sep 19: +102Sep 20: +94Sep 21: +81Sep 22: +77Sep 23: +88Sep 24: +71Sep 25: +64Sep 26: +75Sep 27: +79Sep 28: +75Sep 3Sep 8Sep 13Sep 18Sep 23Sep 28

    +6,151 stars over 75 days across 31 snapshot days; best day +1,207 on Sep 3.

    Forks

    3.5K+640

    Open issues

    245+13

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 15, by 7-day star growth

    google-research/timesfm compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/skills198.5K+3.9K15—
    tradermonty/claude-trading-skills7.6K+2.8K35—
    we-promise/sure17.1K+1.8K40today
    DuarteSantos8/openGym23.1K+1.8K607 days ago
    agent-substrate/substrate8.1K+1.5K651 day ago
    google-research/timesfm35.6K—5179 days ago
    Category median17.1K+1.8K40—

    Also by google-research

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description