{"adoption": {"forks": 387, "observed_at": "2026-08-28T04:05:21.582833+00:00", "stars": 1681}, "canonical_url": "https://ross.abutalabs.com/products/edgeml", "card": {"archived": false, "artifact_type": "library", "description": "This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.", "domain": ["machine-learning", "iot", "embedded-systems"], "enriched": true, "function": ["machine-learning", "deep-learning", "llm-training"], "health_score": 20, "homepage": null, "language": "C++", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["microsoft/EdgeML"], "name": "microsoft/EdgeML", "platform": ["python", "cpp", "cross-platform", "embedded"], "pushed_at": "2024-05-20T12:28:33+00:00", "repo": "microsoft/EdgeML", "stars": 1681, "tags": ["edge-ml", "tinyml", "rnn", "bonsai", "protonn", "fastgrnn", "quantization", "tensorflow", "pytorch", "microsoft-research"], "topics": ["iot-device", "sensor", "edge-machine-learning", "resource-constrained-ml", "machine-learning-algorithms", "microsoft-research", "machine-learning", "tensorflow", "deep-learning", "edge-computing", "microsoft", "edge-devices", "classifier", "emi-rnn", "pytorch", "bonsai", "protonn", "fastgrnn", "cpp", "fastrnn"], "urls": [], "use_cases": ["train tiny classifiers that fit in kilobytes on IoT sensors", "run gesture recognition on microcontrollers", "efficient RNN inference on RAM-constrained devices", "anomaly detection for resource-scarce edge devices", "quantize models to fixed-point arithmetic for embedded inference", "recover critical signatures from time series for fast RNN predictions"], "what_it_is": "A library from Microsoft Research India implementing resource-efficient machine learning algorithms (Bonsai, ProtoNN, FastGRNN, EMI-RNN, DROCC, RNNPool) for edge and IoT devices. It provides TensorFlow and PyTorch packages, C++ inference code, and a fixed-point quantization tool (SeeDot) so tiny models can run offline on microcontrollers.", "when_to_avoid": ["you need state-of-the-art accuracy on large-scale datasets with ample compute", "you want a general-purpose deep learning framework rather than specialized edge algorithms", "you need actively developed features or broad community support"], "when_to_choose": ["you need ML models with kilobyte-scale footprints for IoT or embedded hardware", "you want offline, low-latency predictions without cloud connectivity", "you're working with time-series sensor data on constrained devices"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/edgeml", "repo": "microsoft/EdgeML", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.582833+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:41:26.070734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a31451668c5fc2d3fd3233e89117ed165b4382379817136f73e978dfe8ead26e", "fetched_at": "2026-08-28T04:05:21.582833+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/EdgeML"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3318, "days_push": 835, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}