Llm Safety Python Packages

nemoguardrails

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

deepteam

DeepTeam is a framework to red team LLMs and AI agents.

agent-airlock

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

qwed

Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.

agent-audit

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

csl-core

Find, prove and control the AI agents on your machines: discovers every agent and what it can reach, proves policies with Z3 + TLA+, enforces them deterministically outside the model.

uqlm

[JMLR 2026] UQLM: A Python package for LLM hallucination detection using uncertainty quantification

agentguard-governance

Governance layer for autonomous AI agents — pre-flight checks, runtime monitoring, and post-session reporting.

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.

qwed-legal

🏛️ Deterministic rejection layer for computational legal claims. Verifies dates, amounts, and structured constraints; blocks unproven legal outputs.

jev-pilot

Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)

aetherlab

Official Python SDK for AetherLab - AI guardrails, LLM safety, and content moderation API

simurg

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and garbage mid-stream, before the user sees a bad token. Works with any OpenAI-compatible API.

agentbarrier

Deterministic approval, rejection, cancellation, timeout, replay, and side-effect safety tests for AI agents—no API keys required.

fivedrisk

Per-action AI agent risk scoring and governance. Deterministic 5D scoring, HITL gating, FinOps, Agent Cost Management, Markov drift, audit log. Apache-2.0.

trustllm

[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.

qwed-tax

The Verification Gate for AI-Generated Tax Decisions. Deterministic tax verification layer powered by Z3 and Decimal math — sits between AI agents and execution systems. Not a calculator, not a filing platform.

gateguard-ai

A fact-forcing hook gate for Claude Code. Makes the AI pause and investigate before editing.

neurosym-ai

Neuro-symbolic guardrails for LLMs — injection detection, harm filters, output guards, streaming safety, and action-plan validation.

slimeflow

Python SDK for Slime Flow — biomimetic swarm intelligence coordination layer

blackwall-llm-shield-python

Blackwall LLM Shield is an open-source AI security toolkit for JavaScript and Python that protects LLM apps from prompt injection, sensitive data leaks, unsafe tool calls, and hostile RAG content with prompt sanitization, PII masking, output inspection, policy enforcement, and audit trails.

fortifyroot-ocelle

The core FortifyRoot LLMOps SDK for Python.

brix-protocol

Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the Balance Index, and audit every decision.

molecare-privacy-gate

Keep sensitive prompts local: a 1,024-weight head on bge-m3 that catches health data, credentials and PII written as plain English, which regex and entity tools miss. A second gate for LLM routers and guardrails. Not a medical device.