scryml 0.1.0

Predict infrastructure failure states from a stream of metrics

Scry predicts infrastructure failure states from a stream of metrics. It sorts each resource into one of five operational states, recommends an action for each, and forecasts where the metrics are headed. It is data-source agnostic and runs offline. You bring your own metrics, train your own model, and serve predictions over a small HTTP API. No trained weights ship.

LogicMonitor is one supported adapter, not the anchor. The default path reads Parquet or CSV from local files or object storage. Everything normalizes to one canonical long-format table, so any metric source works once it is in that shape.

The X-DEC model	A dual-encoder temporal VAE plus deep embedded clustering, pure PyTorch, no cloud dependencies. Trains on your own windowed metrics from scratch.
Five operational states	Every resource is sorted into NORMAL, PRE_SCALE, PRE_FAILURE, ACTIVE_DEGRADATION, or ANOMALY, each mapped to a recommended action and priority.
Forecasting	An optional Chronos layer (scryml[forecast]) projects where each metric is headed across multiple horizons, kept behind an extra so the core stays offline-capable.
Data-source agnostic	Read Parquet or CSV from local disk or object storage (S3, GCS, ADLS, MinIO) through DuckDB. The LogicMonitor adapter lives behind scryml[logicmonitor].
A small HTTP service	FastAPI endpoints for prediction, forecasting, drift, anomaly, and accuracy: /predict, /predict/lookup, /forecast, /drift, /anomaly, /accuracy.
Bring your own data	One canonical schema: resource, metric, timestamp, value, plus optional host and datasource fields. Drop your metrics into that table and train. No real telemetry or weights are included.

---

Install

pip install scryml                  # core: the model and the API
pip install "scryml[forecast]"      # add Chronos forecasting
pip install "scryml[logicmonitor]"  # add the LogicMonitor adapter

Or from source with every extra:

git clone https://github.com/ryanmat/scry && cd scry
uv sync --all-extras

Quickstart

End to end on the bundled synthetic sample, no cloud:

# extract windowed features (the sample is dated 2026-01-01)
python scripts/extract_features.py --data examples/sample_data/metrics.parquet \
  --start 2026-01-01 --end 2026-01-02 --profile kubernetes \
  --output data/training_data.npz

# train a model, then serve it
python scripts/train_model.py --data data/training_data.npz --output models/xdec_model.pt
MODEL_PATH=models/xdec_model.pt uvicorn scry.api.main:app --port 8000

curl localhost:8000/health
curl localhost:8000/clusters

Full walkthrough, including a /predict call: examples/quickstart.md.

Documentation

• Architecture: the model, the data seam, and how the pieces fit together.
• Data contract: the canonical metric schema and the ingestion API.
• Ingestion: object storage and the LogicMonitor adapter.
• Training: training locally or on your own orchestrator.

Built with uv, ruff, and pytest on Python 3.10 and up.

License

Apache-2.0.

WAKE UP TO FIND OUT THAT YOU ARE THE EYES OF THE WORLD