tyga-langchain 0.1.2

Safety shield for LangChain — screen agent tool calls before execution

tyga-langchain

Safety shield for LangChain. Wrap any tool with safety_guard() to screen commands before execution.

Install

pip install tyga-langchain

Quick Start

from langchain_community.tools import ShellTool
from tyga_langchain import safety_guard

# One line — wrap any tool
safe_shell = safety_guard(ShellTool())

# Safe commands run normally
safe_shell.run("echo hello")  # hello

# Dangerous commands are blocked
safe_shell.run("rm -rf /")  # BlockedError: Safety Gate 1: matched [rm\s+-rf\s+/]

How it works

1. Gate 1 (local): Regex denylist screens commands in <5ms. Free, no API key needed.
2. Gate 2 (cloud): Set A2A_API_KEY env var to enable LLM judge evaluation via a2ainfrastructure.com.

Get an API key

Sign up free at a2ainfrastructure.com. 500 evaluations/month on the free tier.

Links

• Quick Start Guide
• API Docs

License

Proprietary — Tyga.Cloud Ltd. See LICENSE file.