Metadata-Version: 2.4
Name: sibyl-data
Version: 0.2.0
Summary: Sibyl — Universal Data Intelligence Platform: governed data access SDK + CLI (data-tool)
Author: Akshant
License: Proprietary
Project-URL: Repository, https://github.com/akshant31/sibyl
Project-URL: Issues, https://github.com/akshant31/sibyl/issues
Keywords: data-catalog,semantic-layer,metrics,governance,llm,business-intelligence
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Database
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: fastapi
Requires-Dist: uvicorn[standard]
Requires-Dist: pydantic
Requires-Dist: sqlglot
Requires-Dist: mcp
Requires-Dist: duckdb
Requires-Dist: psycopg[binary]
Requires-Dist: pymysql

# sibyl-data

Sibyl — Universal Data Intelligence Platform: governed data access SDK + CLI (`data-tool`).

Query any data source through one governed semantic layer: the CLI boots the
full engine locally (embedded SQLite metadata, connectors for SQLite /
PostgreSQL / MySQL / files, DuckDB federation), or point it at a remote Sibyl
server.

```bash
pip install sibyl-data
data-tool --help
```

```python
from udip.client import connect

sibyl = connect()                          # local engine
# sibyl = connect(server="http://host:8000", token="sibyl-…")  # remote

print(sibyl.list_datasets())
print(sibyl.ask("total revenue last quarter"))
```

Everything passes through the safety layer (read-only SQL, join caps, row
limits, PII masking) and is written to the audit log. Bearer tokens carry
`query` / `admin` scopes.

Repository: https://github.com/akshant31/sibyl
