Enterprise-grade Zero-Leak Secret Defense & Sandbox for Autonomous AI Agents built with LangGraph, CrewAI, AutoGen, LlamaIndex, and Smolagents.

Documentation • Web Portal • Trust Center • Issues

⚡ Key Features

📦 Installation

pip install agentshield-defense

🚀 Usage Guide

1. The @shield.protect Decorator

from agentshield import shield

@shield.protect
def deploy_infrastructure(target: str, config: str) -> str:
    # Any incoming AWS keys or OpenAI keys in config are automatically masked
    return f"Deployed {target} with token: AKIAIOSFODNN7EXAMPLE"

# When executed:
output = deploy_infrastructure("prod-cluster", "key=sk-1234567890abcdef1234567890abcdef")
print(output)
# -> "Deployed prod-cluster with token: [AGENTSHIELD_REDACTED:AWS_ACCESS_KEY:a1b2c3d4e5f6]"

from agentshield import protect

@protect(strict=True)
def sensitive_operation():
    ...

2. LangGraph & LangChain Integration

from langchain_openai import ChatOpenAI
from agentshield import AgentShieldCallbackHandler

shield_handler = AgentShieldCallbackHandler()

llm = ChatOpenAI(
    model="gpt-4o",
    callbacks=[shield_handler]
)
# Outgoing prompts and tool invocations are inspected and sanitized in real time

3. CrewAI Guardrail Hook

from crewai import Task
from agentshield import AgentShieldCrewHook

hook = AgentShieldCrewHook()

task = Task(
    description="Analyze server environment and deploy database",
    expected_output="Deployment summary"
)

hook.before_task_execution(task)

4. LlamaIndex Callback Handler

from llama_index.core import Settings
from agentshield import AgentShieldLlamaHandler

Settings.callback_manager.add_handler(AgentShieldLlamaHandler())

5. Microsoft AutoGen Message Guard

from agentshield import AgentShieldAutoGenGuard

guard = AgentShieldAutoGenGuard()
clean_message = guard.filter_message(incoming_message)

🔒 Security & Compliance

📄 License