Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 27 of 37

szn-doporucovani-storage-mysql

Security placeholder package

szn-doporucovani-storage-url-normalization

Security placeholder package

szn-doporucovani-storage-zone

Security placeholder package

szn-doporucovani-videoportal-storage-entity

Security placeholder package

szn-doporucovani-videoportal-storage-eventstore

Security placeholder package

szn-doporucovani-videoportal-storage-zone

Security placeholder package

szn-iptv-django-storage-backend

Security placeholder package

szn-libstorage

Security placeholder package

szn-sdn-storageclient

Security placeholder package

szn-zbozi-storage-configuration-parser

Security placeholder package

tbh-secure-agents

Secure Agents Framework with hybrid security validation

theaios-agent-auth

Agent-specific identity and access management for AI agents

threadagentid

Cryptographic identity and reputation for AI agents. Part of the Thread Suite.

trezor-agent

Using Trezor as hardware SSH/GPG agent

trustchain-agent-os

TrustChain Agent OS — Trust-native protocol layer for AI agents

trusted-agent

Run Claude Code inside a podman container, wrapped by gVisor.

trusted-agent-engine

Trusted AI Agent Governance Engine

trustworthy-llm

Core functionality for TLM

truthlocks-anthropic

Truthlocks MAIP wrapper for Anthropic — auto-generate cryptographic receipts for every Claude API call

truthlocks-autogen

Truthlocks MAIP integration for AutoGen — auto-generate cryptographic receipts for every multi-agent conversation

truthlocks-bedrock

Truthlocks MAIP wrapper for AWS Bedrock — auto-generate cryptographic receipts for every model invocation

truthlocks-crewai

Truthlocks MAIP integration for CrewAI — auto-generate cryptographic receipts for every crew task and agent action

truthlocks-langchain

Truthlocks MAIP integration for LangChain — auto-generate cryptographic receipts for every chain and agent action

truthlocks-llamaindex

Truthlocks MAIP integration for LlamaIndex — auto-generate cryptographic receipts for every query and retrieval

truthlocks-openai

Truthlocks MAIP wrapper for OpenAI — auto-generate cryptographic receipts for every API call

tyga-crewai

Safety shield for CrewAI — screen agent tool calls before execution

tyga-langchain

Safety shield for LangChain — screen agent tool calls before execution

typegpt

TypeGPT - Make GPT safe for production

typegpt-light

TypeGPT Light is a reduced version of TypeGPT that uses OpenAI's built-in structured output, but keeps some nice architecture features of TypeGPT.

typegpt-moderation

A client library for the TypeGPT Multimodal Moderation API.

types-boto3-securityagent

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

ultraguard

Enterprise-grade LLM security framework with 40+ scanners and programmable guardrails

umai-agent-sdk

Python SDK for UMAI Agent Mesh Governance and guardrails.

umytbaynazarow-agentauth-sdk

Lightweight, type-safe Python SDK for AgentAuth - Authentication for AI Agents

useagentguard

The Security & Cost Control Layer for AI Agents — Guard, Shield, and Sentinel tiers: budget control, per-agent credential isolation, OAuth scope enforcement, MCP policy enforcement, and compliance reporting.

validate-llm

A composable validation framework for LLM inputs and outputs

vantio-agent-sdk

Vantio Optics Python SDK — shield() for Sight Loop observe. Metadata only; no prompts.

varpulis-agent-runtime

Real-time behavioral guardrails for AI agents

vault-for-agents

Secure credential management for AI agents

vault-pki-agent

Tool for auto-renewal certificates and CRL from Vault PKI.

vaultagent

Permission control for AI Agents — control what your agents can and cannot do.

veriswarm

Official VeriSwarm Python SDK — trust scoring, event ingestion, and agent management for AI agents

veroq-agentmesh

VeroQ Shield adapter for OpenAI Agents SDK + Agent Governance Toolkit — output guardrails, trust scoring, content verification

versyn-litellm

Automatic cryptographic AI decision certification for LiteLLM — SOC2, EU AI Act, GDPR compliance

vexrag

A Red Team framework that evaluates RAG functional correctness when the retrieval backend contains poisoned passages.

weave-protocol-llamaindex

Security scanning and monitoring for LlamaIndex applications - part of Weave Protocol

whylabs-llm-toolkit

Utilities for harm dataset generation

xagentauth

AgentAuth client SDK for Python — authenticate AI agents

xat-langchain

XAT signing for LangChain -- every tool call gets an Agent-Signature header. OpenAPI x-agent-trust.

xshieldai-crewai

xShieldAI / AEGIS DAN gate + budget guard for CrewAI agents — pre-execution governance via @xshieldai/aegis

xshieldai-langchain

xShieldAI / AEGIS DAN gate callback for LangChain agents — pre-execution governance via @xshieldai/aegis

xybern-agent-guard

Framework-agnostic authorization middleware for AI agents

yadacoin-agent-auth

Server-side SDK for the YadaCoin KEL Agent Auth Protocol

yandex-blender-factor-storage

A package to prevent Dependency Confusion attacks against Yandex.

yandex-factor-storage

A package to prevent Dependency Confusion attacks against Yandex.

yandex-uniagent34

A package to prevent Dependency Confusion attacks against Yandex.

yandex-vmagent

A package to prevent Dependency Confusion attacks against Yandex.

yui-agent-guard

Static repository guardrails for agent-touched codebases.

yui-agent-policy

Pure-function policy matrix evaluator for AI coding agents (repo x capability x context -> deny/require_approval/auto_allow).

yuragi-guardrails

Reserved name — install the official package: pip install yuragi

trustcenter-or-securityquestionnaire

TrustCenter | SecurityQuestionnaire review: compare features, pricing, use cases, access model, and alternatives for this AI Security agent in 2026. Sprinto AI’s Free Compliance Kit: Trust Center + AI Security Questionnaire — Free for All

frego

FREGO review: compare features, pricing, use cases, access model, and alternatives for this AI Security agent in 2026. Decentralized AI safety and infrastructure protocol, building safer AI

Guardrails AI

Ensures your AI applications are safe, reliable, and secure.

AiMod

AI leader for safe online communities & marketplaces.

whattheagent

Local-first capability discovery and governance CLI for AI agent workspaces.

@edictum/core

Runtime rule enforcement for AI agent tool calls

@lumin-io/openclaw-diagnostics

Lumin observability + Agent Firewall for OpenClaw — captures prompts, responses, tool I/O, and synchronously enforces firewall policies on every tool call.

@arcjet/next

Arcjet runtime security SDK for Next.js — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF

@flowdot.ai/guardian-agent

TypeScript reference implementation of the guardian-agent spec: a runtime supervisor for tool-using LLM agents (audit log, tool-permission scoping, HITL approval gates, emergency-stop).

@coderifts/sdk

Agent Governance SDK — validate API changes before tool invocations. TypeScript client for the CodeRifts API.

dyolo-kya

TypeScript/Node.js client for dyolo-kya: cryptographic chain-of-custody for recursive AI agent delegation

chromia-guard-sdk

On-chain AI safety infrastructure for autonomous agents. Encrypts actions client-side, submits to Chromia blockchain, and gets AI safety verdicts before execution.

agentclaimguard

A framework-agnostic evidence gate for LLM agent claims.

agentforge-guard-llamaguard

Llama Guard 3 classifier for AgentForge guardrails

agentforge-guard-nemo

NeMo Guardrails programmable rails for AgentForge

agentkavach

Hard budget limits and guardrails for LLM APIs (OpenAI, Anthropic, Google, Mistral).

GPTDetect

Quickly detect AI-generated text and images for free, no sign-up.

aegis-trust

AI agent data access control — control what agents can see. TypeScript port of aegis-trust PyPI (literal name parity).

@agledger/sdk

AGLedger™ SDK: accountability and audit infrastructure for agentic systems.

llm-trust-guard

Comprehensive security guards for LLM-powered and agentic AI applications - 35 guards covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards accessible via unified TrustGuard facade. Features prompt injection (PAP/per

awi-scan

Detect Agentic Workflow Injection risks in GitHub Actions workflows.

@percent20/mist-plugin

Mist — MFA for agentic AI. Claude Code plugin.

@agentic-user-mandate-protocol/aump

TypeScript SDK and validator for the Agentic User Mandate Protocol

zehrava-gate-langchain

Wrap LangChain/LangGraph tools with Zehrava Gate governance — deterministic policy enforcement before any tool executes

shingan-lint

AI Agent Workflow Static Analyzer — detect infinite loops, cost explosions, PII leaks, prompt injection sinks before execution. CLI wrapper that downloads the platform-specific Go binary from GitHub Releases.

@aletheia-labs/auditor

Read-only local auditor CLI/UI for Aletheia governance evidence.

@agenticrail/core

AgenticRail gate client for JavaScript and TypeScript

@connexum/typescript-sdk

TypeScript SDK shim for My Compliance Center. Drop-in replacement for @anthropic-ai/sdk, openai, and @aws-sdk/client-bedrock-runtime with unavoidable governance enforcement.

joy-trust-provider

Trust verification for AI agent handoffs

@auth0/ai-langchain

Auth0 AI for LangChain

palaryn

Palaryn - Model-agnostic infrastructure layer for AI agent I/O security, cost control, and observability

patchgate

Policy enforcement and rollback for AI agent code edits

agent-governance-toolkit-protocols

Protocol implementations (MCP governance, trust protocol, A2A, MCP receipts) for the Agent Governance Toolkit

agent-rag-governance

Retrieval access control and vector store policy enforcement for RAG pipelines

agent-vault-proxy

Deprecated: renamed to keys-on-the-wire. Installing this installs keys-on-the-wire.

authsec-autogen

AuthSec integration for AutoGen — secure AI delegation token retrieval

authsec-crewai

AuthSec integration for CrewAI — secure AI delegation token retrieval

authsec-llamaindex

AuthSec integration for LlamaIndex — secure AI delegation token retrieval

cx-agent-firewall

A lightweight AI agent firewall, audit, and compliance SDK.

Velatir

Pause and approve AI decisions with human oversight. Fast and simple.

More in Security & AI safety