Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 22 of 37

compliant-llm

Tool for testing AI system prompts against various attack vectors

connector-agent-oss

Tamper-proof memory, chain-of-custody, and OS-grade runtime for AI agents

constitutional-agent

Runtime constitutional governance for autonomous AI agents: six gates, twelve hard constraints, cross-session risk composition

crewai-agentlock

AgentLock authorization middleware for CrewAI tool calls.

crewai-amorce

Secure CrewAI crews with Amorce (Ed25519 + HITL + A2A)

crewai-dominion-trust

Trust-gated MCP tool calls for CrewAI via Dominion Observatory

crewai-eydii

EYDII Verify tools and guardrails for CrewAI — verify every agent action before execution

crewai-forge

Forge Verify + Execute tools and guardrails for CrewAI — verify agent actions and track executions with cryptographic receipts

crewai-kavachos

KavachOS DAN gate + budget guard for CrewAI agents — pre-execution governance via AEGIS

crewai-kerq

CrewAI integration for Kerq trust verification — score AI tools before your agents connect.

crewai-kya

KYA (Know Your Agent) identity verification for CrewAI agents

crewai-mcps

Cryptographic security layer for CrewAI MCP tool calls — message signing, replay protection, and tool-pinning

crewai-no-vibes

CrewAI Task guardrail blocking verification claims without evidence — empirical F1 0.815 on MAST mode 3.3

crewai-openterms

OpenTerms adapter for CrewAI — sign and emit ORS v0.1 receipts for tool calls.

crewai-tools-enigmagent

CrewAI tool for EnigmAgent — agents resolve {{PLACEHOLDER}} secrets at the call boundary so LLMs never see real API keys

crewai-trustguard

TrustGuard security integration for CrewAI agents

crowdstrike-aidr-openai

A wrapper around the OpenAI Python library that wraps the Responses API with CrowdStrike AIDR

csp-agent-passport

Verifiable, identity-rooted delegation tokens for AI agents.

datops-agent-sdk

Drop-in trust enforcement for AI agent frameworks — LangChain, CrewAI, OpenAI, and more

detect-llm-api-keys

scan python files for llm api keys (designed for pre-commit)

detect_agent

Detect if code is running in an AI agent or automated development environment

devtrust-agentguard

Policy-as-code runtime for AI agents — audit log + hard-no enforcement.

diplomat-agent

Scan your agentic codebase for unguarded tool calls with real-world side effects

diplomat-agent-ts

Scan TypeScript AI agent code for unguarded tool calls — pip wrapper for diplomat-agent-ts

django-agent-governance

AI governance and PII protection for Django — decorators, audit logs, and LLM-agnostic proxy.

django-agent-trust

A framework for managing agent trust, such as public vs. private computers.

django-llm-middleware

The ONE and ONLY middleware you need for your Django project (cause cybersecurity hard, only use one middleware, no authent!)

django-llm-poison

Serves markov chains to LLM bots.

django-otp-agents

Integration of django-otp and django-agent-trust.

django_fastapi_llm_middleware

The ONE and ONLY middleware you need for your Django or FASTAPI project (cause cybersecurity hard, only use one middleware, no authent!)

dspy-guardrails

A comprehensive collection of AI guardrails built with DSPy for content moderation and security.

dspy-kya

KYA (Know Your Agent) identity verification for DSPy modules

dual-llm-bench

Benchmark prompt-injection resilience and tool safety for dual-LLM agent architectures.

ea-agentgate

Enterprise-grade security gateway for AI agents with middleware, tracing, and auto-rollback

enigmagent

EnigmAgent Python SDK — secure vault integration for AI agent frameworks

entropy0-langchain

Entropy0 Trust Control Plane tool for LangChain agents — evaluate domains and URLs before your agent fetches content from them.

eydii-openai

EYDII Verify guardrail for OpenAI Agents SDK — verify every tool call before execution

fairsense-agentix

An agentic fairness and AI-risk analysis platform for detecting bias in text and images

fastapi-guard-agent

Deprecated alias — the package has been renamed to guard-agent. Installing fastapi-guard-agent will transitively install guard-agent.

findllm

Detect AI-generated text using GPT-2 token prediction analysis

forge-openai

Forge Verify + Execute middleware for OpenAI Agents SDK — verify tool calls and track executions with cryptographic receipts

fortifyos-langchain

FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.

forwagent

GPG/SSH agent forwarder.

gatekeeper-llm

A CLI tool to forge an AI to guard a secret answer, accessible only by a secret question.

gemini-profanity-filter

A Python module for detecting and filtering profanity using Google's Gemini API

gemini_self_protector

Runtime Application Self-Protection

getagentid

AgentID SDK — Identity & verification for AI agents

getagentid-sdk

Official Python SDK for the Agent ID platform

gllm-guardrail-binary

A library containing guardrail components for Gen AI applications.

globus-sdk-tokenstorage

Globus SDK TokenStorage Extension

govagent

The Governance-First Framework for Agentic AI, Enterprise Middleware & OCI Supply Chain Gating

governanceai-guardrails-agent

Official Governance AI Agent Guardrails SDK for Python agents and tool execution

gptzero

Asynchronous Python wrapper for the GPTZero API

gptzzzs

Gptzzzs is a tool that attempts large language model detection evasion by changing grammar.

grantex-crewai

CrewAI integration for the Grantex delegated authorization protocol — scope-enforced, audited agent tools

grantex-openai-agents

OpenAI Agents SDK integration for the Grantex delegated authorization protocol — scope-enforced, audited agent tools

guardian-agent-sdk

Guardian Agent Python SDK for AI Security - Real-time governance for autonomous AI agents

handlebar-claude

Core governance layer for handlebar (https://gethandlebar.com)

handlebar-langchain

AI control layer for Langchain agents

handlebar-openai

Core governance layer for handlebar (https://gethandlebar.com)

hapax-agentgov

[Archived] Early prototype superseded by hapax-systems/reins — Hapax Research Lab

haystack_agentmesh

AgentMesh governance components for Haystack pipelines — policy enforcement, trust scoring, and tamper-evident audit trails

helix-ttd-gemini

Constitutional AI governance utilities for the Helix-TTD Federation

helm-anthropic

HELM governance adapter for anthropic — fail-closed tool calling for AI agents

helm-autogen

HELM governance adapter for autogen — fail-closed tool calling for AI agents

helm-crewai

HELM governance adapter for crewai — fail-closed tool calling for AI agents

helm-langchain

HELM governance adapter for langchain — fail-closed tool calling for AI agents

helm-openai-agents

HELM governance adapter for openai agents — fail-closed tool calling for AI agents

helm-semantic-kernel

HELM governance adapter for semantic kernel — fail-closed tool calling for AI agents

hiddenlayer-langchain-guardrails

Guardrails for LangChain

hiddenlayer-msft-agent-framework-guardrails

Guardrails for MSFT Agent Framework

hiddenlayer-openai-guardrails

Guardrails for the OpenAI Agents SDK

honeypotllm

Protect your LLM API from data theft and model replication using output watermarking and behavioral fingerprinting.

iap-agent

Identity Anchor Protocol SDK for signing requests and offline certificate verification

immunity-agent

Deprecated — renamed to 'prismor'. Installs prismor for you. Run: pip install prismor

intentguard-agent

Agentic AI System That Prevents Costly Digital Mistakes

intercept-agent

Intercept Developer Posture Agent - collects developer environment data

interven-crewai

CrewAI integration for Interven AI firewall. Scan every tool call your CrewAI agents make — block malicious requests, redact PII/secrets, route risky actions to human approval.

interven-langchain

LangChain + LangGraph integration for Interven AI firewall. Scan every tool call your agent makes before it executes — block malicious requests, redact PII/secrets, route risky actions to human approval.

interven-openai-assistants

OpenAI Assistants API integration for Interven AI firewall. Scan tool calls the assistant decides to make before your code executes them.

kanoniv-agent-auth

Cryptographic identity primitives for AI agents - Ed25519 keypairs, DIDs, signed envelopes, and provenance entries

keepassxc-ssh-agent

SSH IdentityAgent proxy that triggers KeePassXC database unlock (TouchID on macOS, biometric/password on Linux)

keeper-secrets-manager-storage

Keeper Secrets Manager SDK helper for managing configurations key-value storage.

keeper-secrets-manager-storage-gcp-kms

Keeper Secrets Manager SDK storage integration with Google Cloud KMS for encrypted key-value storage.

keeper-secrets-manager-storage-oracle-kms

Keeper Secrets Manager SDK storage integration with Oracle Cloud KMS for encrypted key-value storage.

keepkey_agent

Using KeepKey as hardware SSH/GPG agent

kevros-agent-framework

Kevros governance middleware for Microsoft AutoGen and Semantic Kernel agents. Cryptographic action verification, intent binding, and hash-chained provenance for multi-agent workflows. Fail-closed by default.

keychest-agent

Keychest agent

keyhole-agent

Reserved namespace

keystorage

a simple program to manage passwords

keyvault-llm

A simple key management system for development environments

khaos-agent

Chaos engineering and security testing toolkit for AI agents.

kindred-agent-id

Self-custody DID + capability VC profile for AI agents (Python port of @p-vbordei/agent-id)

kya-agent

Know Your Agent — An open standard for AI agent identity, compliance, and auditability

kybershield-claude

KyberShield security integration for Claude and Anthropic SDK

langchain-TMS

A simple security checker for LangChain variables

langchain-aegis

Aegis governance integration for LangChain — add policy enforcement, risk assessment, and audit logging to any LangChain tool.

langchain-agent-governance

Agent runtime governance for LangChain, powered by Cerone.

langchain-agent-memory-guard

LangChain middleware integration for OWASP Agent Memory Guard — runtime defense against AI agent memory poisoning (ASI06)

langchain-agentlattice

AgentLattice governance wrapper for LangChain tools — gate() before every tool execution.

More in Security & AI safety