{"adoption": {"forks": 19764, "observed_at": "2026-08-28T04:12:19.205514+00:00", "stars": 64253}, "canonical_url": "https://ross.abutalabs.com/products/keras", "card": {"archived": false, "artifact_type": "library", "description": "Deep Learning for humans", "domain": ["deep-learning", "machine-learning", "data-science", "computer-vision"], "enriched": true, "function": ["deep-learning", "machine-learning", "llm-training", "data-science"], "health_score": 100, "homepage": "http://keras.io/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["keras-team/keras", "keras-team/keras-core", "keras-team/keras-preprocessing"], "name": "Keras", "platform": ["python"], "pushed_at": "2026-08-26T22:12:59+00:00", "repo": "keras-team/keras", "stars": 64253, "tags": ["neural-networks", "multi-backend", "tensorflow", "pytorch", "jax", "openvino", "model-training", "high-level-api", "natural-language-processing", "linux", "macos", "gpu"], "topics": ["deep-learning", "tensorflow", "neural-networks", "machine-learning", "data-science", "python", "jax", "pytorch"], "urls": [], "use_cases": ["build and train neural networks in python", "train deep learning models on gpu or tpu clusters", "switch between tensorflow pytorch and jax backends", "build computer vision or nlp models with a high-level api", "forecast timeseries with deep learning", "run model inference with openvino"], "what_it_is": "Keras 3 is a multi-backend deep learning framework that runs on JAX, TensorFlow, PyTorch, and OpenVINO, providing a high-level API for building and training neural networks. It supports workloads from laptops to large GPU/TPU clusters across computer vision, NLP, audio, and timeseries tasks.", "when_to_avoid": ["you need low-level control over training loops and graph internals", "you work primarily on Windows without WSL2", "you need inference-only deployment without a backend framework"], "when_to_choose": ["you want a simple, high-level API for deep learning in Python", "you need to train models across multiple hardware backends", "you want to scale from a laptop to datacenter GPU/TPU clusters", "you prefer easy-to-debug eager execution with PyTorch or JAX"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/keras-team/keras", "repo": "keras-team/keras", "role": "main", "score": 98}, {"path": "/repos/keras-team/keras-core", "repo": "keras-team/keras-core", "role": "mirror", "score": 10}, {"path": "/repos/keras-team/keras-preprocessing", "repo": "keras-team/keras-preprocessing", "role": "mirror", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.205514+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:17:25.681009+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "db4fa3c4a3e978c03f53436ae39cc5dc19e7f7f6f7aa3e58025f5aa426e59f92", "fetched_at": "2026-08-28T04:12:19.205514+00:00", "kind": "readme", "missing": false, "url": "https://github.com/keras-team/keras"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 95}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4177, "days_push": 7, "days_rel": 35, "gap_med": 30.0, "n_releases_24m": 23}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}