Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 24 of 37

llm-security

A package for LLM security features

llm-security-firewall

Cognitive Security Middleware - The 'Electronic Stability Program' (ESP) for Large Language Models. Bidirectional containment system with defense-in-depth architecture (6 validation layers), stateful tracking, and mathematical safety constraints. Validated against Unicode/encoding attacks, pattern evasion, multilingual/polyglot attacks (12+ languages including Basque, Maltese), and memory/session attacks. Protocol-based hexagonal architecture with LangChain integration.

llm-sentinel-sdk

Runtime monitoring SDK for AI applications — detect prompt injections and adversarial attacks in production.

llm-shelter

Safety and guardrails toolkit for LLM applications

llm-sign

Provider and client helpers for signed LLM transcript verification

llm-siren

SIREN: lightweight, plug-and-play guard models reading LLM internal representations, for harmful content and for agent trajectories.

llm-stream-guard

Streaming keyword guard for LLM output.

llm-stream-processor

A callback-driven, prefix-safe, lazy LLM stream sanitization library.

llm-taint

Lightweight taint tracking for LLM pipelines — label secrets at entry, block them at unsafe sinks

llm-trust-guard

Security guards for LLM-powered and agentic AI applications. 35 guards, zero dependencies. Covers OWASP Top 10 for LLMs 2025 and Agentic Applications 2026.

llm-watchdog

Production-grade silent failure detection for LLM applications — hallucination alerts, PII leak detection, semantic drift, topic guard, and real-time observability

llm-watermark

easy way to use llm watermarking techniques

llm-watermark-utils

easy way to use llm watermarking techniques

llmarmor

OWASP LLM Top 10 security scanner for AI-powered applications

llmdet

LLMDet: A Large Language Models Detection Tool

llmdr

LLM Detection and Response — tamper-evident audit trails for LLM traffic

llmgateways

Protect OpenAI and Anthropic API calls from prompt injection, jailbreaks, and data-extraction attacks.

llmguardian

Open-source LLM prompt injection defense — protect any AI app in 2 lines of Python

llmjammer

A code obfuscator to confuse LLMs

llmleaks

Security tool for detecting exposed LLM/AI API keys in public repositories

llmosafe

Predictive resource-pressure instrumentation and runtime guardrails for systems processing untrusted inputs

llmsanitize

LLMSanitize: a package to detect contamination in LLMs

llmsec

A Python library for LLM security

llmshield-ai

Lightweight validation, repair, and retry helpers for LLM outputs.

llmvault

Security testing toolkit for LLM prompt injection vulnerabilities

lockllm

Enterprise-grade AI security SDK with prompt injection detection for Python

ls-cred-storage

A package containing storage user credential

market2agent

TVP - Trust Verification Protocol. The background check of the internet.

markllm

MarkLLM: An Open-Source Toolkit for LLM Watermarking

mcp-bastion-anthropic

MCP-Bastion security middleware for Anthropic Claude - prompt injection, PII, and rate-limit protection for AI agents

mcp-bastion-bedrock

MCP-Bastion security middleware for AWS Bedrock - prompt injection, PII, and rate-limit protection for cloud AI agents

mcp-bastion-cohere

MCP-Bastion security middleware for Cohere - prompt injection, PII, and rate-limit protection

mcp-bastion-crewai

MCP-Bastion security middleware for CrewAI - prompt injection, PII, and rate-limit protection for AI agent crews

mcp-bastion-gemini

MCP-Bastion security middleware for Google Gemini - prompt injection, PII, and rate-limit protection

mcp-bastion-groq

MCP-Bastion security middleware for Groq - prompt injection, PII, and rate-limit protection for ultra-fast LLM inference

mcp-bastion-langchain

MCP-Bastion security middleware integration for LangChain - prompt injection, PII, and rate-limit protection for LLM agents

mcp-bastion-llamaindex

MCP-Bastion security middleware for LlamaIndex - prompt injection, PII, and rate-limit protection for RAG pipelines

mcp-bastion-mistral

MCP-Bastion security middleware for Mistral AI - prompt injection, PII, and rate-limit protection

mcp-bastion-openai

MCP-Bastion security middleware for OpenAI - prompt injection, PII, and rate-limit protection for GPT agents

mcpshield-agent

MCPShield Agent - AI Agent Security Scanner for MCP servers

medguard-llm

Healthcare-specific LLM guardrails middleware for clinical safety

mirage-ci

Deterministic policy runtime for AI agents. Same policy file gates CI and enforces in production, with no LLM in the decision loop.

mithril-llm

A firewall for LLMs — block prompt injection, jailbreaks, and PII exfiltration in real time.

moss-anthropic

MOSS cryptographic signing integration for Anthropic Claude

moss-autogen

MOSS cryptographic signing integration for AutoGen

moss-crewai

MOSS cryptographic signing integration for CrewAI

moss-langchain

MOSS cryptographic signing integration for LangChain

moss-langgraph

MOSS cryptographic signing integration for LangGraph

moss-openai

MOSS cryptographic signing integration for OpenAI

mypy-boto3-securityagent

Type annotations for boto3 SecurityAgent 1.44.7 service generated with mypy-boto3-builder 8.12.0

nakata-agentguard

Lightweight agentic loop detector and safety monitor. No LLM required.

neeraj-llmguard

Open-source prompt injection firewall, hallucination blocker, and agent memory layer for any LLM app

nerq-autogen

Trust verification tool for AutoGen multi-agent conversations. Check agent safety before interaction.

nerq-crewai

Nerq trust verification for CrewAI — discover trusted agents and gate tool calls with preflight checks

nerq-langchain

Trust-gate your LangChain agents with Nerq. Preflight trust checks, agent discovery, and trust scoring for 204K+ AI agents.

nerq-langgraph

Trust-check node for LangGraph agents. Verify AI agent safety before execution.

nextpolicyagent

Next Policy Agent — A high-performance, secure policy engine (Python/FastAPI rewrite of OPA)

nextriad-agentshield

The $19/mo Permission Layer for AI Agents - Verify, Control, Audit. Block before execution.

nkit-agents

Production-Ready Safety Layer for Agentic AI - Live observability, pre-execution safety, and audit trails

noma-langchain-integration

Noma guardrail middleware integration for LangChain

nomotic-agent-id

Agent identity primitives for Nomotic-compliant systems

occ-anthropic

OCC cryptographic proof signing for the Anthropic Python SDK

occ-autogen

OCC cryptographic proof signing for AutoGen

occ-crewai

OCC cryptographic proof signing for CrewAI

occ-gemini

OCC cryptographic proof signing for Google Gemini

occ-langchain

OCC cryptographic proof signing for LangChain

occ-llamaindex

OCC cryptographic proof signing for LlamaIndex

occ-openai-agents

OCC cryptographic proof signing for the OpenAI Agents SDK

odoo-addon-web-editor-disable-chatgpt

Web Disable ChatGPT

onlykey-agent

Using OnlyKey as hardware SSH/GPG agent

open-agent-id

Python SDK for Open Agent ID — register, sign, and verify AI agent identities

open-agent-trust

Python SDK for the Open Agent Trust Registry. Verifies agent identity attestations.

openai-agentlock

AgentLock authorization middleware for the OpenAI Agents SDK.

openai-agents-trust

Trust & governance layer for OpenAI Agents SDK — policy enforcement, trust-gated handoffs, and Merkle audit trails

openai-agents-trust-gate

Trust-gated MCP server wrapper for OpenAI Agents SDK via Dominion Observatory

openai-guardrails

OpenAI Guardrails: A framework for building safe and reliable AI systems.

openaiguardrails-sdk

Official Python client for Open AI Guardrails policy distribution, audit evidence, and OPA control-plane APIs.

openclaw-agentlock

AgentLock authorization middleware for OpenClaw skill execution.

openshell_agentmesh

Public Preview - OpenShell + AgentMesh governance skill

org-agentic-toolkit

Governance infrastructure that compiles and validates organization-level agent rules

owasp-agent-security-regression-harness

OWASP harness for executable security regression testing of agentic applications and MCP-integrated systems.

owasp-agentic-mcp

OWASP Top 10 for AI Agents security assessment tools. Capabilities: full agent security scan, prompt injection detection, tool poisoning check, excessive agency, data leakage. Built by MEOK AI Labs.

pallma-guard

The Security Observability Layer for AI Agents

palveron-langchain

Official Palveron LangChain integration — automatic policy enforcement, PII masking, and audit trails for every LLM call.

palveron-openai-agents

Official Palveron integration for the OpenAI Agents SDK — drop-in middleware for policy enforcement, PII masking, and audit trails.

pamagent

Agent for PAM

pandora-llm

Red-teaming large language models for train data leakage

pangea-multipass-langchain

Pangea Multipass authorization library for LangChain

pangea-multipass-llama-index

Pangea Multipass authorization library for Llama Index

pangea-openai

A wrapper around the OpenAI Python library that wraps the Responses API with Pangea AI Guard

passtorage

CLI password generator and manager.

permission-storage-manager

A flexible, high-performance permission storage system for Python applications

pfc-langchain

LangChain adapter that enforces PFC governance at the execution boundary

phellem-autogen

AutoGen adapter for the Phellem security framework

phellem-langchain

LangChain adapter for the Phellem security framework

phellem-semantic-kernel

Semantic Kernel adapter for the Phellem security framework

pilcrow-langchain

The Pilcrow LangChain adapter — deterministic compliance gate for LangChain pipelines.

powerful-agents
pq-ssh-agent

SSH agent protocol with PQ keys

pqagents

Post-quantum cryptographic identity and verification SDK for AI agents.

More in Security & AI safety