Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 21 of 37

agentwall

A dotfile-driven firewall that protects the OS from destructive LLM agent tool calls

agentward

Secure every agent action — from install to runtime. Source-available security platform for AI agents.

agentwarden

Security and access control for AI Agents

agentwrit

Python SDK for the AgentWrit broker -- ephemeral scoped credentials for AI agents via Ed25519 challenge-response

agentx-security-sdk

Runtime firewall for AI agents - watches every tool call, and once switched on blocks the catastrophic ones and tells the agent a safe path.

agi-pragma

AI Action Firewall — seven-stage Decision Intelligence Core for safe agentic AI

ai-agent-audit

OpenTelemetry GenAI traces → EU AI Act Article 12 evidence reports

ai-agent-compliance

Unified installer and compliance documentation for the Agent Governance Toolkit

ai-agent-contracts

A formal framework for governing autonomous AI agents through explicit resource constraints and temporal boundaries

ai-agent-governance

The complete AI agent governance stack - kernel, trust mesh, runtime supervisor, and reliability engineering

ai-agent-passport

Verifiable agent identity with explicit trust and optional A2A integration.

ai-agent-protocol

An SDK for enabling identity authentication and secure encrypted communication between AI agents.

ai-agentguard

Security monitor for AI coding agents — detect hook RCE, MCP poisoning, and API key theft before they execute

ai-security-agent

AI Security Agent AI Agent Directory to Host All AI Security Agent related AI Agents Services, Community, Reviews and More.

aiconfig-extension-llama-guard

An extension for using LLama Guard with aiconfig

air-anthropic-trust

AIR Trust Layer for Anthropic Claude Agent SDK — audit trails, data tokenization, consent gates, and injection detection for EU AI Act compliance

air-crewai-trust

AIR Trust Layer for CrewAI — audit trails, data tokenization, consent gates, and injection detection

air-langchain-trust

AIR Trust Layer for LangChain — audit trails, Gate policy enforcement, consent gates, and injection detection

air-openai-trust

AIR Trust Layer for OpenAI Python SDK — audit trails, PII detection, injection scanning, and HMAC-SHA256 compliance chains for EU AI Act

air-rag-trust

RAG provenance, write gating, and drift detection for AI agents — EU AI Act compliance infrastructure

akto-llm-guard

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.

allow-agent

A lightweight Python framework for agent content moderation.

antarraksha-autogen

Antarraksha AI Agent Enforcement SDK for Autogen

antarraksha-crewai

Antarraksha AI Agent Enforcement SDK for Crewai

antarraksha-langchain

Antarraksha AI Agent Enforcement SDK for LangChain

antarraksha-openai-agents

Antarraksha AI Agent Enforcement SDK for Openai Agents

antarraksha-semantic-kernel

Antarraksha AI Agent Enforcement SDK for Semantic Kernel

apexgate-langchain

Runtime prosocial gating for LangChain agents

aport-agent-guardrails

APort Agent Guardrail — shared core for AI agent and LLM frameworks (pre-action authorization)

aport-agent-guardrails-crewai

APort Agent Guardrail for CrewAI — before_tool_call hook for AI agent and multi-agent crews

aport-agent-guardrails-langchain

APort Agent Guardrail for LangChain/LangGraph — AsyncCallbackHandler for AI agent tool calls

askari-llm

A package to create AI guardrails for LLM applications using YAML-defined policies.

astraguard

Official AstraGuard SDK — license validation, HWID binding, and offline cache for Python server applications

attestable-llm

Attestable LLM → This package is now `aiir`. Install: pip install aiir

aumos-agentshield

Multi-layer agent defense framework for AI security

auth-agent-sdk

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.

auth-agents

Verify AI agent identities with Agent Auth. DID-based authentication using Ed25519 and Verifiable Credentials.

authsec-langchain-sdk

AuthSec identity, delegation, and CIBA approval for LangChain agents

authsec-langgraph-sdk

AuthSec identity and delegation for LangGraph stateful agent workflows

autoagents-guardrails-py

Official Python bindings for AutoAgents Guardrails integration

autogen-kya

KYA (Know Your Agent) identity verification for Microsoft AutoGen agents

autogen-rubric

Post-quantum AI decision attestation for AutoGen, LlamaIndex, and any Python AI pipeline

autogpt-trustguard

TrustGuard security integration for AutoGPT agents

autonomous-agent

数字风控智能体(神荼), 主要负责对用户提交资料进行KYC

awesome-agentguard

Guardrails for AI agents — hallucination detection, tool call validation, circuit breakers, rate limiting, and budget enforcement. One decorator. Any LLM framework.

aws-iam-agent

AI-powered AWS IAM agent with key rotation and Secrets Manager support

aws-iam-security-agent

AWS IAM security agent with GPT-4 for key rotation & secrets management

axor-claude

Claude Code adapter for axor-core governance kernel

axor-langchain

Governance middleware for LangChain 1.0 agents — powered by axor-core compression engines

azureaicommunity-agent-approval

Human-in-the-loop approval gate middleware for AI agent tool calls

azureaicommunity-agent-tool-limit

Global and per-tool call limit enforcement middleware for AI agent pipelines

bastion-llm

A pre-commit security scanner that detects prompt injection vulnerabilities in LLM application codebases through static analysis

beav3r-sdk-langchain

LangChain middleware for routing sensitive tool calls through Beav3r approvals.

bedrock-keys-security

AWS Bedrock and Claude Platform on AWS API keys security toolkit: offline decoder, phantom user discovery, incident response, cleanup, preventive SCPs and detection content.

blackwall-llm-shield-python

Security middleware for Python LLM apps and services. Blocks prompt injection, masks PII, inspects outputs, and gates agent tools.

bpsai-agent-enforce

Enforcement and containment for BPS AI agents

bulwark-agent-security

Enterprise-grade defense framework for AI agents — protects against prompt injection, data exfiltration, and memory contamination.

byted-agent-bytechaos

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-agent-mem

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-agentkit-sdk-python-inhouse-nightly

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-aicoder-agent-evaluate

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-aidp-agent

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-as-agent-harness

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-bytesec-langgraph

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-data-agent-sandbox-sdk

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-feature-storage-offline-tools

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-genius-be-agent-collection

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-genius-be-agent-loop

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-genius-be-code-agent

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-hiagent-common

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-lighten-llm

A small example package

byted-master-data-agent

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-search-byte-rag

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-volc-agent-framework

This is a reserved placeholder package to mitigate dependency confusion risks.

byted-xgpt-triton

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agent-markitdown-cli

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agentbase-cli

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agentchain-lark

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agentcore

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agenthub-sdk

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-agentx

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-aiai-agent-sdk

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-aidp-mllm

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-byted-lv-agent-toolcall-sdk

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-bytedai-langgraph-adapter

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-data-fetch-agent

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-dpflow-browser-agent-mcp

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-dyagent-actionproxy-bin

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-dyagent-sdk

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-eps-biz-agentkit

This is a reserved placeholder package to mitigate dependency confusion risks.

bytedance-gec-llm

This is a reserved placeholder package to mitigate dependency confusion risks.

callmefair

A comprehensive framework for automatic bias mitigation in AI systems

canari-llm

Local-first honeypot token IDS for LLM and RAG applications.

capnagent

Capability-based authority tokens for AI agent tool calls. Python bindings.

cash-search-openai

This is used as a placeholder to help prevent dependency confusion attacks.

cedar-agent-schemas

Canonical Cedar schema library for agent action verbs (exec, open, connect, request_tool). Python helpers for constructing Cedar requests.

ciaf-agents

Identity and Access Management (IAM) and Privileged Access Management (PAM) for AI agents

claude-secret-scan

Secret scanning CLI for Claude Code

claude-skill-auditor

Security auditing tool for Claude Skills - Detect malicious patterns before installing third-party skills

claudeguard

Claude Code security guard - an alternative Claude Code permission framework

More in Security & AI safety