Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 19 of 37

agent-onboard

Official Python SDK for Agent OnBoard — the identity and trust network for AI agents.

agent-operations-sdk

Open-source agent operations SDK — integration discovery, security scanning, autonomy rules, HITL primitives, and capability management for Python agentic systems.

agent-passport-system

Python SDK for the Agent Passport System. Identity, delegation, governance, attribution, mutual authentication, evidentiary type safety, accountability receipts, Cognitive Attestation, Instruction Provenance. Byte parity with the TypeScript SDK.

agent-policy-enforcement-mcp

Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.

agent-policy-engine

Deterministic, capability-based policy enforcement runtime for AI agents

agent-policy-gateway

Policy enforcement and taint tracking for AI agent tool calls.

agent-policy-gateway-mcp

Compliance & guardrails for AI agents — PII filtering, audit logging, GDPR/AI Act checks, kill switch

agent-policy-layer

Agent Policy Layer - Portable, composable policies for AI agents

agent-preflight

Preview and validate AI agent actions before execution.

agent-probe-ai

Agent-level adversarial resilience testing. Tests what others don't: tool interactions, memory poisoning, confused deputy, cost bombs.

agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool arguments, A2A payloads for OWASP LLM01 prompt injection BEFORE they reach a downstream agent. Curated from OWASP + academia + production incidents.

agent-rails

put your agents on guardrails

agent-rbac

Role-Based Access Control for AI Agents with ML-Powered Anomaly Detection

agent-receipts

Python SDK for the Agent Receipts protocol

agent-registry-identity

Registri identity — Ed25519 keypairs, certificates, and cryptographic verification

agent-risk-engine

A layered protocol and reference implementation for codifying risk in autonomous agent actions.

agent-roi

Enterprise policy, identity, approval, audit, observability, adapters, and realized-ROI controls for agentic workflows

agent-runtime-security

Python SDK for agent input scanning, tool-call guardrails, and audit logs

agent-safe

A governance and policy enforcement layer for AI agents and non-human identities

agent-safe-spl

SPL (Safe Policy Lisp) evaluator for Agent-Safe capability tokens. 150 lines, zero deps, microseconds.

agent-safeguards

Safeguards for custom agents.

agent-safety-box

Battle-hardened safety wrapper for AI agents

agent-safety-layer

Production-grade safety boundaries for AI agents - policies, tracing, replay, and human-in-the-loop approval

agent-safety-middleware

One-line safety middleware for AI agent APIs. Prompt injection scanning, cost budgets, decision audit trails. Works with FastAPI, Flask, and any ASGI/WSGI framework.

agent-scope-diff

Risk-focused diffs for agent manifests, MCP configs, and tool permission snapshots.

agent-security-harness

661 security tests for AI agent systems - MCP, A2A, L402, x402, UCP/ACP merchant-journey, AP2 mandate + Fireblocks x402 hardening + Visa TAP / Mastercard Agentic Tokens + denial-of-settlement finality, decision governance, AIUC-1 compliance, NIST AI 800-2 aligned

agent-security-scanner

Security auditing tool for LLM agents, RAG pipelines, and agent frameworks

agent-signature

Agent-Signature HTTP header reference (x-agent-trust scheme). Canonical: x-agent-trust.

agent-signing

A Python package for signing agent setups

agent-skill-evaluator

Evaluate agent skills before you install them. Think 'npm audit' for SKILL.md files.

agent-skill-scanner

Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

agent-status-sdk

Fail-open wrap for live MCP and personal-agent traffic on AgentStatus.

agent-toolprint

Double-signed receipts for AI-agent tool invocations — DSSE + JCS + Ed25519, verifiable offline (Python port of @p-vbordei/agent-toolprint)

agent-trust-langchain

LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning

agent-trust-sdk

Python SDK for AI agent security - threat detection, content scanning, trust verification, and red team testing

agent-trust-stack

Complete Agent Trust Stack — one install for provenance, reputation, agreements, accountability, lifecycle, discovery, and economics

agent-trust-stack-hosted

Hosted trust services for AI agents — CoC Bitcoin anchoring and ATHP mutual verification

agent-trust-telemetry

Trust telemetry middleware for inter-agent communication — makes instruction contamination observable across traces

agent-vault-sdk

Zero-trust credential manager for AI agents — Python SDK

agent-zoo

Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.

agent_governance_toolkit

Public Preview — Unified installer and runtime policy enforcement for the Agent Governance Toolkit

agent_os_kernel

Public Preview — A kernel architecture for governing autonomous AI agents with Nexus Trust Exchange

agentapproved

Runtime compliance evidence for AI agents — one-line SDK, tamper-proof audit trail, multi-framework attestation

agentarc

Advanced policy enforcement layer for AI agents with 3-stage validation, transaction simulation, and security controls

agentarmor

Local-first runtime controls for Python LLM apps and agents: budget circuit breakers, PII/secrets redaction, tool-call policy checks, rate limits, and audit traces — in 2 lines, no hosted proxy.

agentarmor-core

Comprehensive security framework for agentic AI applications — 8-layer defense-in-depth.

agentaudit-sdk

Compliance, governance & observability layer for AI agents

agentauditai-sdk

On-chain EU AI Act compliance SDK for AI agents — immutable audit logs, KYA registration, incident reporting, post-market monitoring.

agentauth-agents

A scalable, framework-agnostic Python authentication library with JWT token management and password reset functionality

agentauth-client

Python SDK for AgentAuth - Authorization layer for AI agent purchases with billing support

agentauth-core

Reserved project name for future AgentAuth Core.

agentauth-py

AI Agent session management SDK

agentauth-sdk

Reserved project name for future AgentAuth SDK.

agentbio

Verify AI agent identity and reputation before interacting with them.

agentbouncr

Python SDK for AgentBouncr — Governance for AI Agents

agentboundary

Open spec and conformance suite for proving AI-initiated production actions

agentbridge-build-sdk

Compliance black box for AI agents - RBI FREE-AI, PMLA 2002, and KYC compliance monitoring

agentcert

Bitcoin-anchored identity certificates for AI agents

agentcheck-sdk

Record what your AI agent is allowed to do

agentcorrect

CI/CD guardrails for AI agents - prevent payment duplicates and data destruction

agentcred

Agent Credit Bureau — trust scoring and audit reports for AI agents and MCP servers

agentcrypt

Symmetric encryption using the ssh-agent

agentctrl

Institutional control layer for AI agent actions — authority, policy, risk, and audit before execution.

agentdid

Cryptographic proof that a human stands behind an AI agent.

agentdojo

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents

agentdojo-core

Core code for AgentDojo

agentdoor

Python Agent SDK for AgentDoor - headless agent authentication

agentdoor-fastapi

FastAPI adapter for AgentDoor - agent authentication middleware

agentegrity

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

agentfacts

The open source SDK for AI agents Identity.

agentfirewall

Runtime firewall for AI agents.

agentforge-guard-llmguard

LLM Guard scanners for AgentForge guardrails

agentfortress

Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents

agentgate-ai

Runtime security for autonomous AI agents

agentgate-pdp

Runtime authorization for autonomous AI agents, with receipts an auditor can verify offline

agentgate-py

Action-level firewall for AI agents — intercepts tool calls before execution.

agentgate-reliability

The reliability layer for AI agents taking consequential actions

agentgate-sdk

The security gateway for AI agents — auth, rate limiting, and policy enforcement in one line.

agentgovern

Compliance-as-code middleware for agentic AI workflows.

agentgraph-agt

AgentGraph trust provider for Microsoft Agent Governance Toolkit

agentgraph-pydantic

AgentGraph trust verification middleware for PydanticAI agents

agentguard-client

Python SDK for AgentGuard — secure API calls for AI agents

agentguard-eu

EU AI Act compliance middleware for AI agents. Make any LLM-powered agent legally deployable in Europe with 3 lines of code.

agentguard-firewall

Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach. Python port of @mukundakatta/agentguard.

agentguard-hermes

AgentGuard security monitoring plugin for Hermes Agent

agentguard-hermes-plugin

AgentGuard security monitoring plugin for Hermes Agent

agentguard-pro

Python SDK for AgentGuard Pro - AI governance and compliance platform

agentguard-py

Monitor and protect yourself with AI agent budget controls, approval workflows, and anomaly detection.

agentguard-runtime

Runtime security firewall for LangChain agents — intercepts tool calls, enforces YAML policy, logs to SQLite.

agentguard-sdk

⚠️ DEPRECATED: This package has been renamed to tealtiger. Install tealtiger instead.

agentguard-spend-hermes

AgentGuard for Hermes Agent: local spend caps, tool guards, sub-agent limits and signed decisions.

agentguard-tech

AgentGuard Python compatibility SDK for HTTP policy evaluation and integration adapters.

agentguard-zhx

Python SDK for AgentGuard - AI Agent governance and monitoring platform

agentguard47

Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn

agentguardinc

Compliance infrastructure for AI agents — runtime monitoring, audit trails, guardrails.

agentguardproxy

Python SDK for AgentGuard — the firewall for AI agents

agentguardx

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

agenthalt

Production-grade guardrails for AI agent function calls. Prevent overspending, unauthorized purchases, unsafe deletions, and more — with Human-in-the-Loop approval.

agentharnessengine

A runtime governance layer that enforces hard behavioral bounds in autonomous agents.

agentic-aegis

Streaming validation shield for AI agents

More in Security & AI safety