AI guardrails & agent security
3,625 agents · most starred first
AI guardrails & agent security, page 21 of 37
A dotfile-driven firewall that protects the OS from destructive LLM agent tool calls
Secure every agent action — from install to runtime. Source-available security platform for AI agents.
Security and access control for AI Agents
Python SDK for the AgentWrit broker -- ephemeral scoped credentials for AI agents via Ed25519 challenge-response
Runtime firewall for AI agents - watches every tool call, and once switched on blocks the catastrophic ones and tells the agent a safe path.
AI Action Firewall — seven-stage Decision Intelligence Core for safe agentic AI
OpenTelemetry GenAI traces → EU AI Act Article 12 evidence reports
Unified installer and compliance documentation for the Agent Governance Toolkit
A formal framework for governing autonomous AI agents through explicit resource constraints and temporal boundaries
The complete AI agent governance stack - kernel, trust mesh, runtime supervisor, and reliability engineering
Verifiable agent identity with explicit trust and optional A2A integration.
An SDK for enabling identity authentication and secure encrypted communication between AI agents.
Security monitor for AI coding agents — detect hook RCE, MCP poisoning, and API key theft before they execute
AI Security Agent AI Agent Directory to Host All AI Security Agent related AI Agents Services, Community, Reviews and More.
An extension for using LLama Guard with aiconfig
AIR Trust Layer for Anthropic Claude Agent SDK — audit trails, data tokenization, consent gates, and injection detection for EU AI Act compliance
AIR Trust Layer for CrewAI — audit trails, data tokenization, consent gates, and injection detection
AIR Trust Layer for LangChain — audit trails, Gate policy enforcement, consent gates, and injection detection
AIR Trust Layer for OpenAI Python SDK — audit trails, PII detection, injection scanning, and HMAC-SHA256 compliance chains for EU AI Act
RAG provenance, write gating, and drift detection for AI agents — EU AI Act compliance infrastructure
LLM-Guard is a comprehensive tool designed to fortify the security of Large Language Models (LLMs). By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.
A lightweight Python framework for agent content moderation.
Antarraksha AI Agent Enforcement SDK for Autogen
Antarraksha AI Agent Enforcement SDK for Crewai
Antarraksha AI Agent Enforcement SDK for LangChain
Antarraksha AI Agent Enforcement SDK for Openai Agents
Antarraksha AI Agent Enforcement SDK for Semantic Kernel
Runtime prosocial gating for LangChain agents
APort Agent Guardrail — shared core for AI agent and LLM frameworks (pre-action authorization)
APort Agent Guardrail for CrewAI — before_tool_call hook for AI agent and multi-agent crews
APort Agent Guardrail for LangChain/LangGraph — AsyncCallbackHandler for AI agent tool calls
A package to create AI guardrails for LLM applications using YAML-defined policies.
Official AstraGuard SDK — license validation, HWID binding, and offline cache for Python server applications
Attestable LLM → This package is now `aiir`. Install: pip install aiir
Multi-layer agent defense framework for AI security
Official Python SDK for Auth Agent - OAuth 2.1 authentication for websites and AI agents. Includes client SDK for Python backends (Flask/FastAPI) and agent SDK for browser automation with browser-use integration.
Verify AI agent identities with Agent Auth. DID-based authentication using Ed25519 and Verifiable Credentials.
AuthSec identity, delegation, and CIBA approval for LangChain agents
AuthSec identity and delegation for LangGraph stateful agent workflows
Official Python bindings for AutoAgents Guardrails integration
KYA (Know Your Agent) identity verification for Microsoft AutoGen agents
Post-quantum AI decision attestation for AutoGen, LlamaIndex, and any Python AI pipeline
TrustGuard security integration for AutoGPT agents
数字风控智能体(神荼), 主要负责对用户提交资料进行KYC
Guardrails for AI agents — hallucination detection, tool call validation, circuit breakers, rate limiting, and budget enforcement. One decorator. Any LLM framework.
AI-powered AWS IAM agent with key rotation and Secrets Manager support
AWS IAM security agent with GPT-4 for key rotation & secrets management
Claude Code adapter for axor-core governance kernel
Governance middleware for LangChain 1.0 agents — powered by axor-core compression engines
Human-in-the-loop approval gate middleware for AI agent tool calls
Global and per-tool call limit enforcement middleware for AI agent pipelines
A pre-commit security scanner that detects prompt injection vulnerabilities in LLM application codebases through static analysis
LangChain middleware for routing sensitive tool calls through Beav3r approvals.
AWS Bedrock and Claude Platform on AWS API keys security toolkit: offline decoder, phantom user discovery, incident response, cleanup, preventive SCPs and detection content.
Security middleware for Python LLM apps and services. Blocks prompt injection, masks PII, inspects outputs, and gates agent tools.
Enforcement and containment for BPS AI agents
Enterprise-grade defense framework for AI agents — protects against prompt injection, data exfiltration, and memory contamination.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
A small example package
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
This is a reserved placeholder package to mitigate dependency confusion risks.
A comprehensive framework for automatic bias mitigation in AI systems
Local-first honeypot token IDS for LLM and RAG applications.
Capability-based authority tokens for AI agent tool calls. Python bindings.
This is used as a placeholder to help prevent dependency confusion attacks.
Canonical Cedar schema library for agent action verbs (exec, open, connect, request_tool). Python helpers for constructing Cedar requests.
Identity and Access Management (IAM) and Privileged Access Management (PAM) for AI agents
Secret scanning CLI for Claude Code
Security auditing tool for Claude Skills - Detect malicious patterns before installing third-party skills
Claude Code security guard - an alternative Claude Code permission framework