Ai Agent Security Python Packages

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

agent-audit-kit

Static scanner for MCP-connected AI agent pipelines — 225 rules across 11 categories, 12 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.

intentprobe

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

marchward

Runtime authority for AI agents. Your agent holds one Marchward key, not your real credentials. Open-core governor: credential mediation, hard cost cap, approval gates, tamper-evident audit. Apache-2.0.

varden

A self-hosted runtime firewall for AI agents

openguardrails

OpenGuardrails (OGR) Python SDK — the openguardrails core runtime. Agent/sandbox instrumentation lives in its own repo: openguardrails-instrumentation-hermes (Hermes + srt/OpenShell).

tealtiger

TealTiger - AI agent security platform with guardrails, cost tracking, and policy management for LLM applications

agentguard-sdk

Powerful protection for AI agents - Open-source security and cost tracking for AI applications

ea-agentgate

Enterprise-grade security gateway for AI agents with middleware, tracing, and auto-rollback

leash

Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.

langchain-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.