Metadata-Version: 2.4
Name: agentic-bq
Version: 0.1.0
Summary: Agent-safe BigQuery client with guardrails, cost controls, and tool wrappers for agentic AI.
Project-URL: Homepage, https://pypi.org/project/agentic-bq/
Project-URL: Source, https://github.com/<your-org>/agentic-bq
Author: Raghava Chellu
License: MIT
License-File: LICENSE
Keywords: agentic-ai,bigquery,google-cloud,guardrails,llm,tools
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Database
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.10
Requires-Dist: google-auth>=2.25.0
Requires-Dist: google-cloud-bigquery>=3.20.0
Provides-Extra: dev
Requires-Dist: mypy>=1.8.0; extra == 'dev'
Requires-Dist: pytest>=8.0.0; extra == 'dev'
Requires-Dist: ruff>=0.6.0; extra == 'dev'
Provides-Extra: pandas
Requires-Dist: pandas>=2.0.0; extra == 'pandas'
Description-Content-Type: text/markdown

# agentic-bq

Agent-safe BigQuery client with guardrails, cost controls, and tool wrappers for agentic AI.

## Why
When LLM agents query BigQuery, you want:
- parameterized queries (no string concat)
- enforced LIMIT
- denylist protection (DROP/DELETE/etc.)
- dry-run cost checks (bytes processed)
- agent-friendly JSON results

## Install
```bash
pip install agentic-bq

