scandar-guard 0.1.0

Runtime security monitoring for AI agents. In-process. No data leaves your environment.

scandar-guard

Runtime security monitoring for AI agents. Drop-in wrapper for Anthropic, OpenAI, LangChain, CrewAI, and AutoGen.

Zero data leaves your environment. All inspection runs in-process.

Install

pip install scandar-guard

Quick Start

from anthropic import Anthropic
from scandar_guard import guard, GuardConfig

client = guard(Anthropic(), GuardConfig(
    agent_id="my-agent",
    asg_telemetry=True,
    asg_api_key="sk_your_key",
))

# Use as normal — Guard monitors every call
response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)

Context Manager (recommended)

from scandar_guard import guard_session, GuardConfig

with guard_session(Anthropic(), GuardConfig(
    agent_id="my-agent",
    asg_telemetry=True,
    asg_api_key="sk_your_key",
)) as client:
    response = client.messages.create(...)
    # session_end telemetry sent automatically on exit

CrewAI

from crewai import Crew
from scandar_guard.integrations.crewai import ScandarCrewAIMonitor

monitor = ScandarCrewAIMonitor(api_key="sk_xxx")

crew = Crew(
    agents=[...],
    tasks=[...],
    step_callback=monitor.step_callback,
    task_callback=monitor.task_callback,
)

AutoGen

from autogen import ConversableAgent
from scandar_guard.integrations.autogen import register_scandar_hooks

agent = ConversableAgent(name="my-agent", ...)
register_scandar_hooks(agent, api_key="sk_xxx")

What it detects

• Prompt injection (direct, indirect, encoded, multi-turn)
• Tool argument injection and data exfiltration sequences
• Privilege escalation and anomalous tool call patterns
• Behavioral profile deviations with per-agent baselines
• 140+ detection rules mapped to OWASP LLM Top 10

Agent Security Graph

When asg_telemetry=True and asg_api_key are set, Guard sends anonymized telemetry (tool names, finding categories, threat scores — never prompts or content) to the Agent Security Graph for fleet-wide visibility.

Links

• Documentation
• Agent Security Graph
• Scandar