Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 33 of 37

agent-boundary-scan

Static analyzer for confused-deputy vulnerabilities in MCP, LangGraph, OpenAI Agents, and CrewAI systems

agent-evidence-guard

Deterministic validation of AI-agent completion claims against evidence and authority requirements.

agent-keybank

Catalog-backed API key loader for coding agents

agent-measurement-card

Signed, verifiable AI-governance measurement card (Ed25519 receipt-spec). Measurement, not certification.

agent-packet

Allowlist-based task packets for Hermes, OpenClaw, and other AI agents

agent-receipt

Offline, bounded claim-to-evidence receipts for agent handoffs

agentaudit-python

EU AI Act Article 12 audit trails for AI agents

agentgap

Read-only reliability and safety auditor for AI agent repositories

agentic-gate

Deterministic schema validation gates and circuit breakers for LLM function calling

agentself

Local identity for an agent: wallet, secrets, and optional email

aicordon-haystack

Check what an LLM is given for prompt injection: material at ingest, and the turn it answers

crewai-tools-deepkeep

DeepKeep AI Firewall guardrails and hooks for CrewAI

keycardai-langchain

LangChain integration for Keycard: delegated, per-tool-call access with brokered credentials

langchain-neuraltrust

LangChain middleware for NeuralTrust TrustGuard

llmsectest

A pytest-native security testing framework for LLM applications (OWASP LLM Top 10).

ragfence

Security testing and authorization-aware retrieval for production RAG systems.

trigguard-litellm

LiteLLM ↔ TrigGuard — PARTIAL callback gate + FULLY_ENFORCED protected_completion path

agentshield

Instant file protection for AI agent operations - hardlink-based zero-copy backup system

agent-threat-rules

Open detection standard -- like Sigma, but for AI agents. Executable rules for prompt injection, tool poisoning, context exfiltration, and MCP attacks. Shipped in Cisco AI Defense. MIT-licensed.

agentauthoritychain

Fail-closed AI-agent authority verification, delegated capability enforcement, and signed decision receipts

agentguard-mcp

A minimal-privilege proxy for MCP tool calls

agentshield-1-sdk

A circuit breaker and runtime protection SDK for AI agents.

conduct-litellm-guard

Runtime governance for AI agents. Conduct Guard as a LiteLLM guardrail — enforce runtime policy on every LLM call routed through LiteLLM.

decionis-autogen

Pre-execution Decionis policy gates for current AutoGen tools and legacy UserProxyAgent.

decionis-crewai

Gate CrewAI tool calls on a signed Decionis Decision Dossier before execution.

litzki-sovp-agentrust-bridge

SOVP to AgenTrust TRACE bridge

llmsafe

Open-source security scanner for AI-powered and agentic applications.

pydantic-ai-deepkeep

DeepKeep AI Firewall custom capability for Pydantic AI

watchlight-claude-agent

Watchlight governance hooks for Claude Agent SDK agents: authorize every tool call and sub-agent spawn before it runs, fail-closed. Model turns are not authorized. Independent plugin, not affiliated with Anthropic.

watchlight-langgraph

Governance primitives for LangGraph agents with Watchlight: authorize gated actions, validate plans, spawn attenuated sub-agents.

watchlight-pydantic-ai

Watchlight governance for Pydantic AI agents: authorize the tools you wrap with guarded_tool() and open every Agent.run as a governed run (nested runs as attenuated sub-agents), fail-closed. Undecorated tools and model turns are not authorized.

@priventai/core

AI agent runtime security: context-preserving tokenization, risk scoring, and policy enforcement

caitlyn

CAITLYN Security Guardian Agent — interactive defense agent for LLM agent protection

tokentrap-ai

Defensive LLM agent honeypot & token tarpit — chat widget, PHP2Shell HTTP decoy, Cloudflare Worker, and Node adapters.

@qerexa/langchain

Gate every LangChain agent action through Qerexa runtime trust enforcement.

@sandboxaq/flintai-sdk-ts

Lightweight SDK for routing AI agent LLM traffic through a guardrails proxy

crewai-heartflow

HeartFlow (心虫) discriminator tool for CrewAI — gate agent output before it reaches users.

@intertrace-runtime/runtime

Intertrace runtime protection SDK — authorize+permit tool gates and agent-builder adapters

@trust-assurance-protocol/sdk

Trust Agent Protocol (TAP) SDK — agent registration, policy evaluation, human review, TAP App passports, audit, and evidence

btp-guard

BTP v7.0.0 Agentic Runtime Protection (ARP) Gateway & MCP Safety Shield - Claude Code, Google GenAI, LlamaIndex, Microsoft AutoGen & Semantic Kernel Middleware, In-Process Tool Invariants, Sub-20µs RAM Gating, and Cryptographic Merkle Vault

acp-pydantic-ai

Agentic Control Plane governance for Pydantic AI agents. One ACPHooks() capability; ACP decides allow/deny/redact on every tool call.

acrostic-agent-watermark

Traceable text watermarking for AI-agent long-form deliverables — anti-leak attribution

agent-approval-interchange

Python support library for the Agent Approval Interchange Specification

agent-blast-radius

Static, pre-deployment analysis of what an agentic system can reach in an AWS account from untrusted model input.

agent-defs

Definitions for agent security tools: public rule sets and risk corpora, scored against outside benchmarks, watched for changes, and preserved after the source disappears.

agent-enrollment-protocol

Official Python SDK for the Agent Enrollment Protocol

agent-guard-python

Outbound change control for AI agents — gate shell, file-write and HTTP side effects before they happen

agent-security-gate-x402

Ultra-low latency (<3ms) deterministic security, prompt injection, Polygon OMS x Solana Pre-Sign Guard, ElizaOS Brain CFR, and Universal Modular Escrow on Polygon, Base, Arbitrum, and Solana Mainnet.

agent-self-edit-gate

Policy-enforced self-edit gateway for coding agents

agent-tool-firewall

Human-in-the-loop approval firewall for Python agent tool calls

agentbastion

A firewall for AI agents: block prompt injection, guard tool calls, redact PII/secrets.

agentic-transfer-verifier

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

agentic-transfer-verifier-harness-extension

Operator-approved digest-only Harness extension for Transfer Verifier.

agentomy-agent

Embedded AI agent governance peer. Standalone or connected to Agentomy infrastructure.

agents-keys

Mint and sign agent Ed25519 keys (did:key). CLI only; no MCP.

ai-agent-handoff-harness-extension

Optional advisory-only AI Agent Handoff extension for Agentic Security Harness.

aicordon-langchain

Check what an LLM is given for prompt injection: material at ingest, tool output, and the turn it answers

airlock-agent

Runtime firewall for AI coding agents — gate every tool call, MCP call and skill against a least-privilege policy.

algovoi-keystone-agent

The agentic behaviour layer for Keystone -- declare rules, behaviours and triggers, deploy them in an Engine, and gate any keystone-connect write; every firing is a content-addressed behaviour_ref (Apache-2.0)

ccs-autogen

Cryptographic runtime receipts for Microsoft AutoGen agents — signed Ed25519 audit evidence for every tool call.

ccs-langchain

Cryptographic runtime receipts for LangChain/LangGraph agents — signed Ed25519 audit evidence for every tool call.

ccs-llamaindex

Cryptographic runtime receipts for LlamaIndex agents — signed Ed25519 audit evidence for every tool call.

ccs-openai-agents

Cryptographic runtime receipts for OpenAI Agents SDK — signed Ed25519 audit evidence for every tool call.

ccs-pydantic-ai

Cryptographic runtime receipts for Pydantic AI agents — signed Ed25519 audit evidence for every tool call. CCS (Correctover Conformance Shape) L1 + behavior receipts.

countersign-agent

Honest human-in-the-loop consent for AI coding agents: you sign the real argv, not the agent's story. Skill census, MCP sampling deny, inbound fence, and a hash-chained receipt of every approval.

derivepassphrase-sshagentsocketprovider

An interface for SSH agent socket providers, which expose an abstract communication channel for an SSH agent to derivepassphrase.

fakesshagent

A non-hardened implementation of the SSH agent protocol, for use in testing.

govern-agent

A policy enforcement layer between AI agents and the infrastructure they act on.

litellm-trufflehog

Simple & fast trufflehog secrets scanning for LiteLLM

llm-host-guard

Audit the attack surface of a machine running local LLMs (Ollama, LM Studio, vLLM, llama.cpp...). Stdlib only.

llm-safety-playbooks

Data-only defensive playbooks and canonical offline advisory policy pack.

onyx-gate-crewai

Onyx Gate for CrewAI — a verifiable authorization gate for crew tool calls: policy-decided allow/deny before a tool executes, with an audit trail you can re-check.

phb-agentledger

A tamper-evident, hash-chained audit ledger for AI agent actions.

prema-agentshield

Autonomous Security & Zero-Trust Governance Guardian for Enterprise AI Agent Fleets by Prema AI Labs

qerexa-langchain

Gate every LangChain agent action through Qerexa runtime trust enforcement.

raginject

Evaluation harness for indirect prompt injection and retrieval poisoning resistance in RAG pipelines

safeprompt-langchain

LangChain integration for SafePrompt: prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.

yanez-agent-authorization

Yanez agent authorization: request human approval, verify signed receipts.

@fidacy/mcp

The AI Agent Firewall. Enforce signed authority before consequential actions and protect sensitive data at the execution boundary. Free API key required.

nostr-agentic-identity

The standard for agentic identity on Nostr, plus a thin, dependency-light conformance primitive: the identity types, the act-outward gate predicate (owned + self + verified + funded), and a pure structural conformance checker. ESM + CommonJS.

@aporthq/aport-agent-guardrails

APort Repository Guard and pre-action authorization guardrails for GitHub, Claude Code, Cursor, Codex, Gemini CLI, Goose, OpenClaw, LangChain, CrewAI, DeerFlow, and n8n

agentic-firewall

MCP policy gateway and red-team benchmark harness

agentkey

Authorization and evidence SDK for AI agents: check permissions before every action, record what agents actually did.

crewai-relayshield

Pre-execution gate for CrewAI: check an MCP server or package with RelayShield before an agent connects to it

emilia-smolagents

Exact-action authorization receipt checks for Hugging Face smolagents tools.

solystopia-agent-preflight

Deterministic pre-deployment checks for AI agent systems. Blocks unsafe designs before they ship.

valet-fs

Keep API keys on your phone and lend them to an AI agent's machine — in memory only, never on disk, and only while you allow it.

detect-agent

Detect if code is running in an AI agent or automated development environment

@backbond/agent-scan

Local deterministic pre-attachment security scanner for MCP and AI-agent tool manifests.

ai-agent-sudo

Tiny provider-neutral authorization checkpoint for AI-agent actions: allow / deny / require_approval.

@404labs/securitycheck

Pre-commit secret scanner. Blocks API keys, tokens, .env files, and private keys from leaking into git. Ships as a skill for Claude Code, OpenAI Codex CLI, Google Antigravity, and Moonshot Kimi CLI, plus a standalone CLI / git hook.

@rigour-labs/mcp

MCP server + live dashboard for AI code governance — OWASP LLM Top 10 (10/10), real-time MCP App UI, 25+ security patterns, Bayesian learning Brain, hallucinated import detection, multi-agent governance. Works with Claude, Cursor, VS Code, ChatGPT, Goose,

agent-custody

Proof of what your AI agents did. Give your agents real power, without losing control of them. The Python client of the agent-custody sidecar.

agent-harness-aibom

AIBOM generator for AI agent harnesses (Hermes, OpenClaw) and their model/skill/MCP/hook surface

agent-killswitch

Operational safety controls for autonomous AI agents - kill switch, heartbeat, circuit breaker

agentcreds

Verifiable, attenuable delegation for AI agents - org-rooted and verified offline

agentcreds-runtime

Runtime AgentCreds agent-identity enforcement for tool calls - MCP middleware and agent-to-agent (A2A) verification

agentmemorytaintgap

Flags AI agent code that persists untrusted tool/external/user content into long-term memory with no sanitization or provenance marker (agent memory poisoning).

agentprahari

A robust, enterprise-grade, drop-in security & safety guardrail layer for AI agents and LLMs.

agentveto

Runtime control for AI agents - replay any run, prove what happened, veto what must not happen.

More in Security & AI safety