Runtime Security Python Packages

hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

plugin-scanner

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

arcjet

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

arcjet-sensitive-info-rampart

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

mobsf

Mobile Security Framework (MobSF) is an automated, all-in-one mobile application (Android/iOS/Windows) pen-testing, malware analysis and security assessment framework capable of performing static and dynamic analysis.

vulnify

Python SDK and CLI for Vulnify: check an AI agent action and get ALLOW, REVIEW or BLOCK before it runs. Adapters for CrewAI and LangGraph.

agentegrity

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

varden

Runtime security, governance and policy enforcement for AI agents

pyrasp

PyRASP is a Runtime Application Self Protection package for Python-based Web Servers (Flask, FastAPI and Django), Serverless Functions (AWS Lambda, Azure and Google Cloud Functions) and MCP Servers (FastMCP)

clampd

Runtime security SDK for AI agents — guard tool calls in 1 line

agent-gorgon

Runtime policy guard for AI agent processes: watches process, file, and network activity from user space, applies deterministic policy, and attempts SIGSTOP or SIGKILL on reviewed triggers — no SDK required, works against any PID. Audit-only mode rehearses policy first; every decision logged as evidence.

aegis-openai

Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Every decision is ed25519-signed and Merkle-anchored for tamper-evident audit. 12 microservices, sub-30ms p95, OWASP LLM Top-10 coverage.

aegis-anthropic

Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Every decision is ed25519-signed and Merkle-anchored for tamper-evident audit. 12 microservices, sub-30ms p95, OWASP LLM Top-10 coverage.

adrian-sdk

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

aegis-langchain

Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Every decision is ed25519-signed and Merkle-anchored for tamper-evident audit. 12 microservices, sub-30ms p95, OWASP LLM Top-10 coverage.

yana-ai

Yana AI 🐰 One runtime. Any AI. Human-governed. A local-first, cross-platform system for running, connecting, orchestrating, and governing AI — with deterministic control over what it can access, change, and execute. Your AI can act. But who decides how far it can go?

agentcontainment

A runtime-enforced containment layer for AI agents: detect, prove, halt, contain, map, and recover without trusting the agent to enforce its own boundaries.

patronus-api-client

Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsafe tool activity across Codex, Claude Code, and DeepSeek Harness.

bluerock-oss

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.

aegis-bedrock

Runtime security & governance control plane for AI agents. Enforces per-tool authorization, OPA policy, behavioral risk scoring, blast-radius analysis, autonomy contracts, and tenant kill-switch. Every decision is ed25519-signed and Merkle-anchored for tamper-evident audit. 12 microservices, sub-30ms p95, OWASP LLM Top-10 coverage.

rai-governance-platform

WhitePact — open-source runtime authority for AI agents and autonomous systems. Intelligence may propose; WhitePact decides.

acgs

ACGS Governed System— runtime governance broker for autonomous agent execution

norviq

Runtime security platform for LLM agent tool calls on Kubernetes

skillfence

Runtime behavioral security for Agentic Skills — deterministic policy engine, human-in-the-loop gate, full OWASP Agentic Skills Top 10 (AST01–AST10) coverage. Not another SKILL.md scanner: traces what a skill actually does, not what it claims.