Metadata-Version: 2.4
Name: llamafirewall
Version: 1.0.0
Summary: LlamaFirewall is a framework designed to detect and mitigate AI centric security risks, supporting multiple layers of inputs and outputs, such as typical LLM chat and more advanced multi-step agentic operations. It consists of a set of scanners for different security risks.
Author-email: LlamaFirewall Team <llamafirewall@meta.com>
License-File: LICENSE
Requires-Dist: codeshield>=1.0.1
Requires-Dist: huggingface-hub>=0.30.2
Requires-Dist: numpy>=2.1.1
Requires-Dist: openai>=1.76.0
Requires-Dist: pydantic>=2.11.3
Requires-Dist: torch>=2.4.1
Requires-Dist: transformers>=4.51.3
Requires-Dist: typer>=0.15.2
