Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 25 of 37

pqc-agent-wallet

Quantum-resistant credential wallet for AI agents. ML-KEM-768 key encapsulation, AES-256-GCM at rest, ML-DSA signed access audit log. LangChain/AutoGen/CrewAI integrations.

pqc-rag-signing

PQC-signed RAG pipeline chunks. Sign document chunks with ML-DSA at ingestion, verify at retrieval. Prevents vector database poisoning.

probeagent-ai

Offensive security testing for AI agents

prompt-defender-llm-defences

Prompt Defender. A package to help you defend against prompt injection attacks.

prompt-firewall-groq

Production-ready LLM security firewall powered by Groq

proofgate-agentkit

ProofGate Action Provider for Coinbase AgentKit - Blockchain guardrails for AI agents

protectrag

Evals and observability for RAG: prompt-injection screening on stored documents

purifyllm

purifyllm

py-agent-kernel

A security boundary for LLM agents — policy, audit, and rollback for every tool call

pyagentguard

Helmet.js for AI Agents — Lightweight security middleware for production AI agents

pyagentshield

Prompt injection detection for Agents using ZEDD (Zero-Shot Embedding Drift Detection)

pydantic-ai-eydii

EYDII Verify tools and middleware for Pydantic AI — verify every agent action before execution

pydantic-ai-forge

Forge Verify tools and middleware for Pydantic AI — verify every agent action before execution

pydantic-ai-guardrails

Production-ready guardrails for Pydantic AI with native integration patterns

pydantic-ai-shields

Guardrail capabilities for Pydantic AI — cost tracking, tool permissions, input/output guards

pydantic-ai-toolguard

Deny-first tool authorization for pydantic-ai agents — by AgentsID

pydantic-aioredis-db

Benign slopsquatting research package

pydantic_ai_agentmesh

Governance middleware for PydanticAI — semantic policy enforcement, trust scoring, and audit trails for agent tool execution

pydetectgpt

Easy to use Python library for detecting AI-generated text

pyvault-agent

Python implementation of Vault Agent with client-side caching and automatic authentication

qortara-governance-langchain

Qortara Governance — LangChain sidecar SDK. Deep tool-dispatch interception + Portable Trust Attestations + policy enforcement companion to LangSmith.

quilr-litellm-guardrails

Quilr Guardrails Integration for LiteLLM

quint-agent

Behavioral telemetry and policy enforcement for AI agents

rag-context-guard

Middleware that prevents sensitive information leakage in RAG pipelines by analyzing the context assembly graph

rag-firewall

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

rag-guard-enterprise

Enterprise-grade data poisoning detection & alerting for RAG systems

rag-sanitizer

Scan RAG documents for hidden prompt injections, invisible text attacks, and data exfiltration payloads before they enter your vector database.

rag_control

A runtime governance, security and execution control layer for Retrieval-Augmented Generation (RAG) systems.

ragbits-guardrails

Guardrails module for Ragbits components

ragcompliance

Audit trail middleware for RAG pipelines in regulated industries

ragdefender

Efficient defense against knowledge corruption attacks on RAG systems

raguard

Security middleware for RAG pipelines — detect adversarial hallucination attacks before they reach your LLM.

rare-agent-sdk

CLI tooling for Rare agent identity flows

rciam-federation-registry-agent

A library that connects to ams using argo-ams-library and syncs with MITREid, SimpleSAMLphp and Keycloak

redforge-llm

Adversarial testing for LLM applications. Pip install. Async-first. Reproducible.

rends-agent-sdk

Runtime interception SDK for AI agent governance

repello-agent-wiz

Generate agentic workflows visualizations & threat modelling reports for your agentic projects.

resk-llm

Comprehensive security toolkit for LLM applications - https://resk.fr

rotagent

Agent authentication and orchestrator client utilities for secure multi-agent communication

rubrik-agent-cloud-policy-plugin

Rubrik Agent Cloud policy enforcement plugin for AI agent frameworks

safe-llm

Coming soon

safeGPT

A safer way to use GPT chat models

safeagent-exec-guard

AI agent execution guard with durable claims, request-id deduplication, unresolved-outcome handling, and receipts.

safedeepagent

World's Most Comprehensive Secure Agentic AI Framework - 12 Security Foundations, Continual Learning, Multi-LLM Support

safellmkit

Universal Guardrails SDK for Large Language Models

safety-agent

A lightweight Python guardrail SDK for content safety

safewise-agent

Using SafeWISE as hardware SSH/GPG agent

safewiseagentlib

Using hardware wallets as SSH/GPG agent

sbo3l-autogen-keeperhub

Microsoft AutoGen Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

sbo3l-crewai

CrewAI tool wrapping SBO3L — gate every Crew action through SBO3L's policy boundary.

sbo3l-crewai-keeperhub

CrewAI Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

sbo3l-langchain

LangChain Python tool wrapping SBO3L — gate every agent payment intent through SBO3L's policy boundary.

sbo3l-langchain-keeperhub

LangChain Python tool that gates KeeperHub workflow execution through SBO3L's policy boundary. Composable with sbo3l-sdk.

sbo3l-langgraph

LangGraph adapter for SBO3L — drop a PolicyGuardNode between your plan and execute nodes to gate every action through SBO3L's policy boundary.

sbo3l-llamaindex

LlamaIndex tool wrapping SBO3L — gate every agent payment intent through SBO3L's policy boundary.

scopeblind-llamaindex

Ed25519 signed receipts for LlamaIndex agent tool calls

scopeblind-pydantic-ai

Ed25519 signed receipts + Cedar policy enforcement for Pydantic AI agents

scopeblind-swarms

Ed25519 signed decision receipts for kyegomez/swarms multi-agent systems. Wrap any tool in a Swarms agent with tamper-evident, offline-verifiable receipts in the Veritas Acta format (IETF draft-farley-acta-signed-receipts).

scrub-llm

Drop-in LLM secret scrubber to prevent API key and credential leaks

secret-agent

An agent for handling secrets in config

secret-storage

Tools for extract sensitive configuration out of your project

secrets-storage

Typed secret lookup from environment variables and HashiCorp Vault

secureagentics

Reserved package name for Secure Agentics

securellm

AI Security Operations Platform — Python SDK & Security Gateway

security-agent-sdk

Python SDK for Security Agent specifications (models and JSON Schemas)

securityagent-core

Local-first DLP engine and security layer for AI coding agents. Secures Copilot, Claude Code, Cursor, Windsurf, and any MCP-compatible agent.

selfxyz-agent-sdk

Python SDK for Self Agent ID — proof-of-human verification for AI agents

sentinel-llm-security

SENTINEL — AI Security Platform. 49 Rust Engines + Micro-Model Swarm. Defense, Offense, Framework.

sessiongpt

Generates an AWS IAM session policy given a description of the tasks the user needs to perform.

shopee-securityaz-kms-agent

A small example package

smolagents-kya

KYA (Know Your Agent) identity verification for HuggingFace smolagents

sologate-langchain

Governance gate for LangChain agents. Powered by Sentinel AI — pauses risky actions for human approval, logs every decision, generates compliance reports.

soul-agent-validator

Rules-as-Markdown AI agent governance validator. 35 compliance checks, A2A v1.0 (Linux Foundation) compatible, soul.py powered.

soulpolicy-langgraph

LangGraph node bindings for SoulPolicy drift / guardrail primitives

sprk3-defend-agents

Runtime security for AI agents — detects jailbreak, prompt injection, and tool misuse from inside the agent.

sq-llm-checker

This is used as a placeholder to help prevent dependency confusion attacks.

sq-llm-guardrails

This is used as a placeholder to help prevent dependency confusion attacks.

sr-agent-wallet

Drop-in middleware that gives AI agents hard spending limits, token budgets, circuit breakers, and real-time kill switches.

ssh-agent-keyring

A Python keyring backend unlocked by ssh-agent signatures

stripllm

LLM sanitization SDK — DOMPurify, but for LLM context windows.

structural_authz_agentmesh

AgentMesh adapter for structural authorization gates — consumes external policy decisions, trust grades, and delegation scope chains as AGT trust signals

stryda-langchain

Drop Stryda governance into a LangChain agent — wrap a BaseTool, or attach a callback to an AgentExecutor.

stryda-langgraph

Stryda governance as a LangGraph node — plug it between the agent LLM and the tool executor.

sudoagent

Runtime guardrail for tool/function calls: policy, optional approval, and a verifiable ledger.

swarm-probe

Adversarial resilience testing for multi-agent ecosystems

swarm-safety

SWARM: System-Wide Assessment of Risk in Multi-agent systems - A Distributional AGI Safety framework

swarm-shield

Swarm Shield - TGSC

swarmauri_auth_idp_apple

Apple OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_azure

Azure Active Directory OAuth 2.0 / 2.1 / OIDC 1.0 login implementations for Swarmauri deployments

swarmauri_auth_idp_cognito

AWS Cognito OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_facebook

Facebook OAuth 2.0 / OAuth 2.1 / OIDC 1.0 login implementations for Swarmauri

swarmauri_auth_idp_gitea

Gitea OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_github

GitHub OAuth 2.0 / OAuth 2.1 identity provider implementations for Swarmauri

swarmauri_auth_idp_gitlab

GitLab OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_google

Google OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_keycloak

Keycloak OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_auth_idp_okta

Okta OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_cert_acme

ACME certificate service for Swarmauri

swarmauri_cert_cfssl

CFSSL-backed certificate service for Swarmauri

swarmauri_cert_ocspverify

OCSP certificate verification service for Swarmauri.

More in Security & AI safety