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 LLM systems.

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).

agent-airlock

Open-source security firewall for AI agents — validates tool calls, strips ghost arguments, enforces type safety, PII masking, RBAC, cost tracking & sandbox isolation. Works with LangChain, OpenAI Agents SDK, PydanticAI & CrewAI.

uqlm

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

gateguard-ai

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

qwed-finance

Deterministic verification middleware for banking and financial AI. NPV, IRR, loan amortization, and interest calculations with QWED precision.

agi-pragma

AI Action Firewall — seven-stage Decision Intelligence Core for safe agentic AI

agent-audit

Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 49 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.

qwed

The Deterministic Verification Protocol for AI - 11 verification engines for math, logic, code, SQL, facts, images, and more. Now with Agentic Security Guards.

lintlang

Static linter for AI agent configs, tool descriptions, and system prompts with zero-LLM CI gating

neurosym-ai

Neuro-symbolic guardrails for LLMs: rules + repair loops + (optional) SMT.

csl-core

Deterministic policy language for AI agents. Z3 + TLA+ dual-engine formal verification. Runtime enforcement <1ms.

brix-protocol

Runtime Reliability Infrastructure for LLM Pipelines

openbias

Reliability layer for AI agents - monitors workflow adherence and intervenes when agents deviate

guardex

Guardex - AI Control Plane for autonomous agents (closed source)

blackwall-llm-shield-python

Security middleware for Python LLM apps and services. Blocks prompt injection, masks PII, inspects outputs, and gates agent tools.

jailbreakeval

A collection of automated evaluators for assessing jailbreak attempts

opensentinel

Reliability layer for AI agents - monitors workflow adherence and intervenes when agents deviate

ioa-core

Intelligent Orchestration Architecture Core - Open-source platform for orchestrating modular AI agents with memory-driven collaboration and governance mechanisms

medguard-llm

Healthcare-specific LLM guardrails middleware for clinical safety

qwed-legal

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

custom-guardrails

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

reprobe

Phase-aware LLM activation steering and linear probing. A memory-efficient, practical implementation of Representation Engineering (RepE) for safety research.