Ai Safety Python Packages

pydantic-ai-middleware

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.

agent-governance-toolkit

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

agent-os-kernel

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

agentmesh-platform

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

agent-hypervisor

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

agent-sre

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

agentmesh-runtime

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

styxx

Cognitive observability for LLM agents. Nine calibrated cognometric instruments — pure-Python, MIT, no LLM required. 9-for-9 on K=1 phase transition. Every Mind Leaves Vitals (DOI 10.5281/zenodo.19777921).

vibelign

AI coding safety CLI for vibe coding workflows. Checkpoints, undo, anchors, MCP, and secret protection for Claude Code, Cursor, Codex, and OpenCode.

enterprise-rag-patterns

Cross-industry compliance patterns for RAG pipelines: FERPA, HIPAA, GDPR, NIST AI RMF, OWASP LLM Top 10, and more. Vector store adapters, framework integrations, and audit logging.

etzchaim

A diagnosable brain for your LLM. Cognitive architecture in the SOAR/ACT-R/CLARION/LIDA lineage, for the LLM era. Apache 2.0.

mcpsafetywarden

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

agentmesh-primitives

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

xsafeclaw

Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

anywhere-agents

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

eu-ai-act-scanner

MCP EU AI Act Compliance Scanner - Open source tool to detect EU AI Act violations in codebases

uqlm

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

soma-ai

The nervous system for AI agents. Behavioral monitoring, pressure graphs, and directive control.

leashd

Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.

pytector

Easy to use LLM Prompt Injection Detection and Prompt Input Sanitization / Detector Python Package with support for local models, API-based safeguards, and LangChain guardrails.

selectools

Production-ready Python framework for AI agents with built-in guardrails, audit logging, cost tracking, and hybrid RAG. Supports OpenAI, Anthropic, Gemini, Ollama. By NichevLabs.

agent-audit-kit

Security scanner for MCP-connected AI agent pipelines — 77 rules, 13 scanners, OWASP Agentic 10/10, GitHub Action, SARIF, compliance mapping