AI guardrails & agent security
3,625 agents · most starred first
AI guardrails & agent security, page 22 of 37
Tool for testing AI system prompts against various attack vectors
Tamper-proof memory, chain-of-custody, and OS-grade runtime for AI agents
Runtime constitutional governance for autonomous AI agents: six gates, twelve hard constraints, cross-session risk composition
AgentLock authorization middleware for CrewAI tool calls.
Secure CrewAI crews with Amorce (Ed25519 + HITL + A2A)
Trust-gated MCP tool calls for CrewAI via Dominion Observatory
EYDII Verify tools and guardrails for CrewAI — verify every agent action before execution
Forge Verify + Execute tools and guardrails for CrewAI — verify agent actions and track executions with cryptographic receipts
KavachOS DAN gate + budget guard for CrewAI agents — pre-execution governance via AEGIS
CrewAI integration for Kerq trust verification — score AI tools before your agents connect.
KYA (Know Your Agent) identity verification for CrewAI agents
Cryptographic security layer for CrewAI MCP tool calls — message signing, replay protection, and tool-pinning
CrewAI Task guardrail blocking verification claims without evidence — empirical F1 0.815 on MAST mode 3.3
OpenTerms adapter for CrewAI — sign and emit ORS v0.1 receipts for tool calls.
CrewAI tool for EnigmAgent — agents resolve {{PLACEHOLDER}} secrets at the call boundary so LLMs never see real API keys
TrustGuard security integration for CrewAI agents
A wrapper around the OpenAI Python library that wraps the Responses API with CrowdStrike AIDR
Verifiable, identity-rooted delegation tokens for AI agents.
Drop-in trust enforcement for AI agent frameworks — LangChain, CrewAI, OpenAI, and more
scan python files for llm api keys (designed for pre-commit)
Detect if code is running in an AI agent or automated development environment
Policy-as-code runtime for AI agents — audit log + hard-no enforcement.
Scan your agentic codebase for unguarded tool calls with real-world side effects
Scan TypeScript AI agent code for unguarded tool calls — pip wrapper for diplomat-agent-ts
AI governance and PII protection for Django — decorators, audit logs, and LLM-agnostic proxy.
A framework for managing agent trust, such as public vs. private computers.
The ONE and ONLY middleware you need for your Django project (cause cybersecurity hard, only use one middleware, no authent!)
Serves markov chains to LLM bots.
Integration of django-otp and django-agent-trust.
The ONE and ONLY middleware you need for your Django or FASTAPI project (cause cybersecurity hard, only use one middleware, no authent!)
A comprehensive collection of AI guardrails built with DSPy for content moderation and security.
KYA (Know Your Agent) identity verification for DSPy modules
Benchmark prompt-injection resilience and tool safety for dual-LLM agent architectures.
Enterprise-grade security gateway for AI agents with middleware, tracing, and auto-rollback
EnigmAgent Python SDK — secure vault integration for AI agent frameworks
Entropy0 Trust Control Plane tool for LangChain agents — evaluate domains and URLs before your agent fetches content from them.
EYDII Verify guardrail for OpenAI Agents SDK — verify every tool call before execution
An agentic fairness and AI-risk analysis platform for detecting bias in text and images
Deprecated alias — the package has been renamed to guard-agent. Installing fastapi-guard-agent will transitively install guard-agent.
Detect AI-generated text using GPT-2 token prediction analysis
Forge Verify + Execute middleware for OpenAI Agents SDK — verify tool calls and track executions with cryptographic receipts
FortifyOS runtime protection for LangChain and LangGraph agents — zero code changes required.
GPG/SSH agent forwarder.
A CLI tool to forge an AI to guard a secret answer, accessible only by a secret question.
A Python module for detecting and filtering profanity using Google's Gemini API
Runtime Application Self-Protection
AgentID SDK — Identity & verification for AI agents
Official Python SDK for the Agent ID platform
A library containing guardrail components for Gen AI applications.
Globus SDK TokenStorage Extension
The Governance-First Framework for Agentic AI, Enterprise Middleware & OCI Supply Chain Gating
Official Governance AI Agent Guardrails SDK for Python agents and tool execution
Asynchronous Python wrapper for the GPTZero API
Gptzzzs is a tool that attempts large language model detection evasion by changing grammar.
CrewAI integration for the Grantex delegated authorization protocol — scope-enforced, audited agent tools
OpenAI Agents SDK integration for the Grantex delegated authorization protocol — scope-enforced, audited agent tools
Guardian Agent Python SDK for AI Security - Real-time governance for autonomous AI agents
Core governance layer for handlebar (https://gethandlebar.com)
AI control layer for Langchain agents
Core governance layer for handlebar (https://gethandlebar.com)
[Archived] Early prototype superseded by hapax-systems/reins — Hapax Research Lab
AgentMesh governance components for Haystack pipelines — policy enforcement, trust scoring, and tamper-evident audit trails
Constitutional AI governance utilities for the Helix-TTD Federation
HELM governance adapter for anthropic — fail-closed tool calling for AI agents
HELM governance adapter for autogen — fail-closed tool calling for AI agents
HELM governance adapter for crewai — fail-closed tool calling for AI agents
HELM governance adapter for langchain — fail-closed tool calling for AI agents
HELM governance adapter for openai agents — fail-closed tool calling for AI agents
HELM governance adapter for semantic kernel — fail-closed tool calling for AI agents
Guardrails for LangChain
Guardrails for MSFT Agent Framework
Guardrails for the OpenAI Agents SDK
Protect your LLM API from data theft and model replication using output watermarking and behavioral fingerprinting.
Identity Anchor Protocol SDK for signing requests and offline certificate verification
Deprecated — renamed to 'prismor'. Installs prismor for you. Run: pip install prismor
Agentic AI System That Prevents Costly Digital Mistakes
Intercept Developer Posture Agent - collects developer environment data
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.
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.
OpenAI Assistants API integration for Interven AI firewall. Scan tool calls the assistant decides to make before your code executes them.
Cryptographic identity primitives for AI agents - Ed25519 keypairs, DIDs, signed envelopes, and provenance entries
SSH IdentityAgent proxy that triggers KeePassXC database unlock (TouchID on macOS, biometric/password on Linux)
Keeper Secrets Manager SDK helper for managing configurations key-value storage.
Keeper Secrets Manager SDK storage integration with Google Cloud KMS for encrypted key-value storage.
Keeper Secrets Manager SDK storage integration with Oracle Cloud KMS for encrypted key-value storage.
Using KeepKey as hardware SSH/GPG agent
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
Reserved namespace
a simple program to manage passwords
A simple key management system for development environments
Chaos engineering and security testing toolkit for AI agents.
Self-custody DID + capability VC profile for AI agents (Python port of @p-vbordei/agent-id)
Know Your Agent — An open standard for AI agent identity, compliance, and auditability
KyberShield security integration for Claude and Anthropic SDK
A simple security checker for LangChain variables
Aegis governance integration for LangChain — add policy enforcement, risk assessment, and audit logging to any LangChain tool.
Agent runtime governance for LangChain, powered by Cerone.
LangChain middleware integration for OWASP Agent Memory Guard — runtime defense against AI agent memory poisoning (ASI06)
AgentLattice governance wrapper for LangChain tools — gate() before every tool execution.