Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 20 of 37

agentic-audit

Python SDK for AgenticAudit — open-source compliance monitoring for AI agents

agentic-behavioral-contracts

Behavioral validation toolkit for AI agents in regulated environments. Checks whether agents follow the correct process — not just whether they produce correct outputs.

agentic-contract

Policy engine for AI agents

agentic-guard

Static analyzer for prompt injection and confused-deputy risks in LLM agent code.

agentic-identity

Cryptographic trust anchor for AI agents

agentic-profile-auth

Agentic Profile Authentication Library

agentic-sentinel

Agent Governance Layer - Middleware for AI agent action control

agentic-shield

Security scanner and runtime firewall for AI agents and MCP servers

agentic-store-mcp

Model Context Protocol (MCP) Server for AI Data Privacy: LLM prompt firewall, audit logs, and 74 MCP tools for Claude, Codex, Cursor, and Windsurf.

agenticontrol

AGENTICONTROL V0 MVP - Control plane for AI agents with synchronous blocking and asynchronous logging

agentid

Python SDK for verifying AI agent credentials issued by AgentID

agentid-protocol

Identity, discovery, trust, and runtime for AI agents

agentid-sdk

Enterprise Python SDK for AI guardrails, PII/secret masking, workflow telemetry, and audit logging.

agentidcard

Official Python SDK for Agent ID Card - AI agent identity credentials

agentidentity-1

Agent Identity Systems Python SDK

agentidentity-auth

Cryptographic identity for AI agents. Verifiable Ed25519 tokens replacing hardcoded API keys.

agentintent

Trust infrastructure for AI agents - AI should do what it says, we make sure it does

agentity-auth

Agentity OIDC authentication — verify human owners via Google, GitHub, Apple, Microsoft

agentiva

Runtime safety for AI agents: intercept tool calls, policy scoring, and audit logging

agentkeyring

Python client for AgentVault — AI-native credential vault for autonomous agents.

agentkeys

Python SDK for AgentKeys — proxy API calls through a secure credential vault

agentkeys-io

Python SDK for AgentKeys — proxy API calls through a secure credential vault

agentlattice

Governance SDK for AI agents — audit trails, policy engine, approval gates.

agentlaw

Law-first governance kit for AI coding agents: installable scaffold + memory MCP server that lets agents read project rules before they write code.

agentlens-scanner

Pre-Installation AI Agent Tool Risk Analyzer

agentlock

Authorization framework for AI agent tool calls. Your AI agent needs a login screen. AgentLock is that login screen.

agentlock-sdk

AgentLock Python SDK for AI agent integration

agentmesh-mesh

Agent security mesh: 27-endpoint proxy + 12 framework SDKs + coding-agent hooks, composing 54 Tessera modules with SPIRE, agentgateway, and OpenTelemetry.

agentmesh_discovery

Shadow AI agent discovery and inventory for the Agent Governance Toolkit

agentmint

Runtime enforcement library for AI agent tool calls

agentnotary

Notarize, govern, and audit AI agents — cryptographic seal, runtime guard, and EU AI Act compliance docs

agentoath

The open protocol for AI agent identity, trust, and notarization.

agentoath-registry

AgentOath Registry Server -- MVP

agentoath-shadowos

AgentOath trust protocol adapter for ShadowOS -- automatic trust receipts for AI agent operations.

agentomy

Governed agent framework for Python. Add governance to any AI agent.

agentpass

An execution gateway for AI agents on untrusted devices

agentpass-ai

Replay-safe authentication middleware for autonomous AI agents

agentpass-identity

AgentPass Python SDK for identity and access management

agentpassport

Trust and authorization layer for multi-agent systems

agentpassport-registry

Trusted agent registry with AgentCard signature verification

agentpin

Domain-anchored cryptographic identity protocol for AI agents

agentpki

Python SDK for AgentPKI — cryptographic identity for AI agents. PASETO v4 passports, Ed25519 signing, RFC 9421 HTTP Message Signatures.

agentpolicy

Runtime policy enforcement for AI agent sessions

agentpress-core

Zero-dependency parser for agents.txt v1.0. The reference Python implementation.

agentpress-static

agents.txt for any repo. Tell autonomous AI agents what they're allowed to do, in 60 seconds.

agentpriv

sudo for AI agents - allow, deny, or ask before any tool runs

agentproof-ai

LLM-capability CAPTCHA and obfuscated verification challenges for Python applications.

agentsaegis-config-sync

AgentsAegis security training package. Safe, empty package used for trap command training.

agentsaegis-deploy-utils

AgentsAegis security training package. Safe, empty package used for trap command training.

agentsaegis-env-loader

AgentsAegis security training package. Safe, empty package used for trap command training.

agentsafe-sdk

Real-time URL trust scoring for AI agents

agentscrub

Scrub secrets and credentials from AI coding assistant session logs

agentseal

Security toolkit for AI agents - machine scan for dangerous skills/MCP configs + prompt injection/extraction testing

agentseal-gateframe

GateFrame AgentSeal — Cryptographic evidence receipts for AI agent decisions

agentseal-sdk

Tamper-proof audit trails for AI agents.

agentsec

Security infrastructure for autonomous AI agents

agentsec-core

Shared security primitives for AI agent protection

agentsec-eval

Security assessment framework for AI agents — adversarial test runner + server-side audit + scoring

agentsec-firewall

Policy-enforced firewall for AI agent tool calls

agentsecrets

Python SDK for AgentSecrets — zero-knowledge secrets infrastructure for AI agents

agentsecrets-cli

AI-native zero-knowledge secrets manager

agentsecure

Local-first security runtime for AI coding agents

agentsentinel-autogen

Security scanner for AutoGen multi-agent conversations — powered by AgentSentinel on SingularityNET

agentsentinel-core

Safety controls for AI agents — budgets, approvals, rate limits, and audit logs

agentsentinel-crewai

Security scanner for CrewAI multi-agent workflows — powered by AgentSentinel on SingularityNET

agentsentinel-langgraph

Security scanner for LangGraph agent workflows — powered by AgentSentinel on SingularityNET

agentsentinel-sdk

Runtime authority and control for autonomous AI agents

agentshield

Security and monitoring for AI agents

agentshield-ai

Monitor and protect your AI agents in production

agentshield-api

Secure middleware SDK for AI agents.

agentshield-app
agentshield-audit

Trust Infrastructure for AI Agents – Security audits, cryptographic certificates, and Trust Handshake Protocol

agentshield-cli

Mode 1 AgentShield Clean CLI

agentshield-client

Alias package — installs agentshield-guard, the official AgentShield Python SDK.

agentshield-core

Prompt injection & tool call security middleware for agentic LLM systems

agentshield-firewall

AgentShield Enterprise AI Agent Security Firewall

agentshield-fw

The runtime firewall for AI agents. Protect any agent in 3 lines of code.

agentshield-guard

Official Python SDK for AgentShield — prompt-injection detection for LLM agents.

agentshield-langchain

LangChain callback handler that emits signed verdict envelopes for every tool call.

agentshield-py

Alias package — installs agentshield-guard, the official AgentShield Python SDK.

agentshield-pythonv2

Python SDK for AgentShield — AI agent spend control

agentshield-runtime

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.

agentshield-sdk

Python SDK for the AgentShield API - Runtime security for agentic AI applications.

agentshield-vigil

The Identity-First Security Firewall for AI Agents

agentshield-x

A policy-enforcing reference monitor for AI agent tool calls.

agentsid

Identity and auth for AI agents — drop-in MCP middleware

agentsim-sdk

AgentSIM Python SDK — autonomous OTP relay for AI agents

agentstamp

Python SDK for AgentStamp — trust verification, identity stamps, and reputation scoring for AI agents.

agentsteer

Runtime protection for AI coding agents

agentsts-adk

Framework-specific integration points with agentsts-core

agentsts-core

Security Token Service client implementing RFC 8693 OAuth 2.0 Token Exchange

agentsudo

The permission layer for AI agents. Enforce scopes, approvals, and safe tool use across LangChain, LlamaIndex, FastAPI, and custom agents.

agentsudo-core

Zero Trust Security Middleware for AI Agents

agentsystems-notary

Cryptographic notarization SDK for LLM interactions

agenttrust

Runtime security, observability, and compliance for AI agents

agentveil

Python SDK for routed AI-agent action decisions, approvals, receipt records, and bounded evidence

agentverif-sign

✅ Sell verified agents. Buyers trust verified packages. Unsigned agents get ignored. Add verification in seconds.

agentvet-py

Validate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises ToolArgError with LLM-friendly retry hint. Python port of @mukundakatta/agentvet.

agentvisor

~/.ssh/agent for AI agents

agentvoy-guard

Runtime guardrails enforcement for AI agents — reads agent.guard.yml and enforces limits at runtime

More in Security & AI safety