Spaces:
Running
Running
Organization card
Browse files
README.md
CHANGED
|
@@ -35,6 +35,11 @@ df = pd.read_parquet("hf://datasets/QuantFeatures/hyperliquid-hourly-features/da
|
|
| 35 |
|
| 36 |
Field definitions, timestamp semantics, and coverage: [Feature Catalog](https://github.com/QuantFeatures/FeatureCatalog).
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
## Full data on request
|
| 39 |
|
| 40 |
Continuous history for Hyperliquid and Binance, in two ways:
|
|
|
|
| 35 |
|
| 36 |
Field definitions, timestamp semantics, and coverage: [Feature Catalog](https://github.com/QuantFeatures/FeatureCatalog).
|
| 37 |
|
| 38 |
+
## Built for AI
|
| 39 |
+
|
| 40 |
+
- **Model-ready inputs:** point-in-time features with no look-ahead, explicit missing values, and standard Parquet that loads with `datasets` or pandas.
|
| 41 |
+
- **Agent-ready:** an MCP (Model Context Protocol) server lets AI assistants and agents discover features by meaning, read exact definitions, check coverage, and fetch point-in-time rows. Available to customers on request.
|
| 42 |
+
|
| 43 |
## Full data on request
|
| 44 |
|
| 45 |
Continuous history for Hyperliquid and Binance, in two ways:
|