Safety Python Packages

nemoguardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

cpex

A policy enforcement runtime for AI agents

stata-mcp

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

safetext

Fast profanity word, curse word, swear word, bad word filtering tool for English, Spanish, Chinese, Turkish and more.

skjold

Security audit Python project dependencies against security advisory databases.

agentic-security-harness

Test whether AI agents keep repo text, tools, memory, and audit trails inside their authority boundaries; outputs traces, scorecards, and remediation reports.

simpleaudit

Allows to red-team your AI systems through adversarial probing. It is simple, effective, and requires minimal setup.

safety-harness

A perception-grounded safety harness for physical AI actuators: default-deny precondition gate, permission not detection.

schema-mcp-core

Ядро для MCP-серверов из каталога эндпоинтов: поиск методов, классы доступа, HTTP-клиент, хранилище ключей | Core for schema-driven MCP servers: method search, access classes, HTTP client, key storage.

fmdtools

System Resilience Modelling, Simulation, and Assessment in Python

acgs-lite

Constitutional governance membrane between agent reasoning and side effects. No valid Decision Receipt, no side effect. Apache-2.0, Beta. Not an agent framework.

nazeyatta

Command-line preflight and post-action verification checker for AI workers and automation. Explicit UNKNOWN/VERIFIED states, PASS/REVIEW/BLOCK, reproducible receipts. 👈😽

pyisomme

Tools for ISO-MME file format (merge, report, calculate, CFC-filter, ...)

hpl-specs

High-Level Property Specification Language

agent-integrity-proto

Agent Integrity Protocol — real-time thinking block analysis for AI agent alignment

jmo-security

JMo Security Suite - Terminal-first security audit toolkit with many tools, multi-target scanning, & compliance

qwed-finance

Deterministic verification layer for AI-generated financial decisions. Verifies math (NPV, IRR, Black-Scholes, YTM, VaR), compliance (AML/KYC via Z3), and banking schemas (ISO 20022, SWIFT) — fail-closed, proof-backed. Not execution. Verification.

loom-agent

Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.

agentos-platform

Deterministic record, replay, and git-bisect for AI agent runs. Reproduce a broken run byte-for-byte offline, then binary search to the commit that broke it.

aimarket-provenance

15 AIMarket hub plugins — TEE escrow, channels, reputation, safety, and more.

agentarmor

The full-stack safety layer for AI agents. Budget limits, prompt injection shields, PII filtering, output firewalls, and hooks — in 2 lines of code.

qarai-agent-guard

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt injection, jailbreaks, and adversarial attacks.

cato-cli-py

Portable sandbox for AI agents and untrusted commands. One config, any process, anywhere.

qarai-agent-guard-langchain

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt injection, jailbreaks, and adversarial attacks.