TensorFlow is Google’s open-source machine-learning framework, released under Apache-2.0 and used for training and serving models across platforms.
CHOOSE A PRODUCT · BUILD WITH YOUR AGENT
TensorFlow is Google’s open-source machine-learning framework, released under Apache-2.0 and used for training and serving models across platforms.
Catalog categories: machine_learning_framework.
Catalogued capability areas: - Tensor computation with GPU/TPU acceleration - Keras high-level training API - Serving, mobile (Lite) and browser (TF.js) runtimes
This summary reflects the catalog record, not a complete product specification. Verify intended users, end-to-end workflows, supported platforms, edge cases, data handling, and constraints against cited sources. Treat capability labels as research leads until that verification is complete.
3 candidate projects in the landscape. A candidate may cover all, part, or none of what TensorFlow does — read the coverage and gaps below.
TensorFlow is already free and open source.
The product is the open-source project.
Open framework and the dominant research ecosystem.
Independent open alternative.
Open numerical/ML framework from Google.
Functional, XLA-based.
Alternative coverage
Available (already open source). Apache-2.0, with open alternatives in PyTorch and JAX.
The gap
None in licensing — the framework is already open source.
This Markdown file is the coding-agent skill for TensorFlow. Give it to your agent in your project; it guides research, reuse decisions, implementation and verification.
Give the TensorFlow skill to your coding agent in your project. Ask it to evaluate TensorFlow itself ↗ against your needs, reuse what fits, then follow the skill's build and verification instructions.
Give the product skill to your coding agent in the project where you want to build. Optional starter workspace: rae build product google-tensorflow --out ./google-tensorflow. CLI reference.
