Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 30 of 37

agentscanner

Static security scanner for agentic AI configuration: settings, permissions, hooks, MCP servers, agents, skills, and steering files (Checkov for AI agent stacks).

agentsec-cli

Static security scanner for AI coding agents and MCP configurations

agentshield-security

AI Agent Runtime Security Sandbox

agenttoolguard

AI Agent security guard - policy engine for LLM tool calls

agentworth

Python client for the AgentWorth governance gate (REST over the HTTP ingress)

agentx-mcp

Keyless MCP security shield: wrap any MCP server so every tools/call is screened and recorded; set the posture to enforce and a blocked call comes back as coaching your agent recovers from. Launcher for agentx-security-sdk.

agora-agent-receipts

Tamper-evident, third-party-verifiable receipts for AI agent / MCP tool calls

akeyless-agentcore-runtime

Fetch Akeyless secrets at runtime on AWS Bedrock AgentCore using cloud identity authentication

aragora-verify

Standalone offline verifier for Open Decision Receipts (ODR) -- check schema, JCS canonical digest, Ed25519 signature, and hash-chain linkage with no Aragora install or account.

banking-agent-audit

Governance patterns for autonomous AI agents in regulated banking

cloakllm-verifier

Standalone, dependency-light verifier for CloakLLM audit artifacts -- verify hash chains, Ed25519 signatures, key provenance, RFC 3161 timestamps, and compliance reports WITHOUT the full SDK or trusting CloakLLM's code.

cogniify-agentwatch

AgentWatch SDK — AI agent governance, audit, and policy enforcement

cre-agent-audit

Reference architecture for AI agent governance in commercial real estate operations — Autonomy Ladder™ patterns, MIT-licensed.

crewai-signatrust

CrewAI tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.

cwn-crewai-trust-gate

CrewAI tools for the Trust Gate MCP server: signed receipts, a read-only-allowlist decision gate, an egress marker check and an exit drill.

cwn-langchain-trust-gate

LangChain tools for the Trust Gate MCP server: signed receipts, a read-only-allowlist decision gate, an egress marker check and an exit drill.

cwn-llama-index-trust-gate

LlamaIndex tools for the Trust Gate MCP server: signed receipts, a read-only-allowlist decision gate, an egress marker check and an exit drill.

datagate-llm

The inference boundary layer between your data and outbound AI requests

emilia-crewai

Guard CrewAI tools with EMILIA Protocol — require an offline-verifiable authorization receipt (EP-RECEIPT-v1) before an irreversible tool runs: missing -> refused, valid -> runs, replay -> refused, forged -> refused (RR-1).

finserv-agent-audit

Governance patterns for autonomous AI agents in regulated financial services

fost-agent-ledger

Finite operational ledger toolkit for AI-agent support, omissions, obligations, certificates, environment assumptions, and transitions.

gaas-langchain

LangChain and LangGraph integration for GaaS (Governance as a Service)

gaas-openai-agents

OpenAI Agents SDK integration for GaaS (Governance as a Service)

governed-agents

A governance harness for autonomous AI agents: a human proposal-gate, budget caps, an independent watchdog, and a full audit trail.

guardrails-ai-llamaguard-7b

A llama based validator which checks whether a given prompt is safe/unsafe by specifying a set of policies and lists the violating policies when applicable.

holdmyagent

Self-hosted, fail-closed approval server for AI agents (Arbiter)

infill-bedrock

Identity-based security framework. Every node is a user. Everything between is encrypted at rest.

langchain-comply54

LangChain / LangGraph integration for comply54 — African AI agent compliance enforcement

langchain-signatrust

LangChain tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.

langchain-tool-gate

Tool governance and auditing framework for LangChain

llm-firewall

A lightweight, domain-aware safety firewall for LLM applications — works with any API or local model, with dynamic policy-document support.

llm-guardrails-kit

A compliance control layer between your app and any LLM: PII/PCI redaction, cost tracking, and privacy-safe audit logging. GCC-focused.

llm-security-scanner

OWASP Top 10 for LLMs security scanner — fully offline

openagentontology

Auto-generate a governance ontology, Trust Profile, and signed badge for any agent, MCP server, repo, OpenAPI, Rego, or workflow. The OpenTelemetry for agent governance.

openai-agents-signatrust

OpenAI Agents SDK tools for Signatrust — cryptographically signed, tamper-evident AI Decision Receipts.

payer-agent-audit

Governance patterns for autonomous AI agents in health-insurance / payer operations (aligned to the NAIC Model Bulletin framework)

payments-agent-audit

Governance patterns for autonomous AI agents in regulated payments

private-capital-agent-audit

Governance patterns for autonomous AI agents at SEC-registered investment advisers (private capital)

py-agentbrake

Circuit breaker SDK for LLM agents.

rag-redteam

Red-team your RAG pipeline for prompt injection and source-document leakage, in CI.

swarmauri_auth_idp_aws

AWS IAM Identity Center OAuth 2.0 / 2.1 login implementations for Swarmauri

swarmauri_auth_idp_salesforce

Salesforce OAuth 2.0 / OAuth 2.1 / OIDC 1.0 identity provider implementations for Swarmauri

swarmauri_pop_dpop

DPoP proof-of-possession tooling for Swarmauri services

swarmauri_pop_x509

X.509 mutual TLS proof-of-possession verifier for Swarmauri

@rexymayderio/sentinel

Universal Security Verification Framework for AI Agent Installations

skillpin

Trusted dependency manager for AI agent skills

@emilia-protocol/openai-agents

Turn the OpenAI Agents SDK human-in-the-loop tool-approval step into a verifiable, offline-checkable EMILIA authorization receipt. OpenAI pauses an agent and asks for approval; EMILIA makes that approval portable, tamper-evident evidence — a named human a

ratify-agents

A unified contract layer for LLM agents — declarative, parameterizable contract templates enforced by deterministic checks and LLM judgment.

reeflex-claude

Reeflex adapter for Claude Code: a PreToolUse hook that gates every tool call on its impact before it runs (allow/hold/deny), fail-closed -- governance that protects you from your own agent.

telescope-llm-text-detection

Improving Zero-Shot Detection of LLM-Generated Content With Token Repetition

@phinq/phinq

The runtime checkpoint for AI agents — inspect every tool call, hold the irreversible for approval, keep verifiable evidence of human oversight.

@agentright/core

AgentRight scoring engine — pre-deployment governance assessment for AI agents

agentright

Pre-deployment governance scanning for AI agents. Scan configs, get trust scores, gate deployments.

3tears-agent-acl

shared rbac evaluator + cache for the 3tears platform: groups, roles, role assignments, evaluation trails

3tears-agent-audit

unified audit envelope, fire-and-forget publish helper, and the audit erasure rule and hub anonymization request for the 3tears platform

ecz-id-agents

Inspects AI agent projects for ECZ-ID configuration and public evidence posture.

mandatedev-agent

The Mandate Agent SDK — Trust Engine for the Agent Economy

vouch-langgraph

Sign LangGraph tool calls and graph nodes with Vouch Credentials.

@weave_protocol/langchain

LangChain.js security integration for Weave Protocol - callbacks, tool wrappers, and retriever guards

@makerchecker/connector-langchain

MakerChecker connector for LangChain that wraps a StructuredTool so every invocation runs a deny-by-default governance check and records to the hash-chained audit log.

@lupid/sdk

TypeScript/JavaScript SDK for the Agentum engine — agentic governance & IAM enforcement

@letterblack/lbe-core

Local-first execution governance SDK for AI agents.

lelu-agent-auth

TypeScript SDK for Lelu — the authorization engine for autonomous AI agents

doberman-agent

Framework-agnostic middleware for approving or denying AI agent tool calls.

guardllm-tr

Open-source security guardrails for LLM applications — prompt injection, jailbreak, PII, hallucination & toxicity detection (with Turkish/KVKK support).

guardrails-ai-provenance-llm

A validator for ensuring the factuality and reducing brand risk in generated content.

@panguard-ai/panguard-mcp-proxy

MCP Proxy — runtime interception for AI agent tool calls using ATR rules

@intutic/proxy

Native high-performance AI agent governance proxy binary

@cellfence/plugin-agent-budget

CellFence rule plugin for AI agent change budgets.

maqam

Open-source AI agent governance for TypeScript: policy, exact one-use approvals, controlled tool execution, and verifiable receipts.

@absolutejs/agent-control

Authenticated AI agent operator API, console, and bound plan-then-execute playground.

@agentapprove/openclaw

Agent Approve plugin for OpenClaw - approve or deny AI agent tool calls from your iPhone and Apple Watch

@agentadmit/sdk

AgentAdmit SDK: user-mediated AI agent authorization for Node.js apps

@absolutejs/agency

Provider-agnostic AI agent authorization with policy, approvals, rejections, durable delegation, execution leases, receipts, kill switches, and signed handoffs.

@agent-seal/sdk

Give your AI agent a signed, verifiable identity in one line.

@axtary/actionpass

Scoped, signed ActionPass artifacts for runtime-governed AI agent actions.

octopus-inspect

Catch governance holes before production does. A static governance linter for AI agent workspaces.

@cendor/sdk

Build an LLM agent with spending limits, a tamper-evident audit trail, PII redaction, and record/replay testing built in from the start — a governed agent in about 10 lines.

agent-approval-gate

Human-in-the-loop approval gate for LLM agent tool calls. Classify tools read/write, block destructive calls behind an approver, and never persist a grant across turns.

toolgovern-integration-langgraph

Route LangGraph.js tool calls through toolgovern's governTool() gate before they reach ToolNode -- wraps each tool with the classifier, then re-wraps it with LangChain's own tool() factory so it slots into new ToolNode([...]) unchanged.

@kakunin/langchain

Kakunin compliance tools for LangChain JS/TS — verify agent certificates and scopes inside tools and chains

@mastyf_ai/langchain-middleware

Mastyf AI security middleware for LangChain — intercepts and evaluates tool calls through the Mastyf policy proxy

@visiq/harness

VisIQ agent-governance harness for Node.js — action governance, retrieval governance, and audit-trail reporting, added to your existing agent framework by one visiq() call.

@noinjection/langchain

NoInjection enforcement adapter for LangChain structured tools.

@queldrex/enforce

Drop-in enforcement for AI agents — authorize every tool call through the Queldrex Trust Layer (allow / require approval / deny) before it runs, in code or as an inline MCP gateway. Fail-safe, zero-dependency.

@fidacy/langchain

The AI Agent Firewall for LangChain. Enforce signed authority before consequential tool calls. Free account-owned API key required.

sphinx-agent

Sphinx — local-first secret guard CLI for terminal + AI workflows

@ory/cloudflare-agents

Ory Agent Security for the Cloudflare Agents SDK — per-tool authorization, tracing, and identity propagation by wrapping the AI SDK tools passed to streamText. Built on @ory/argus.

@nyxora-sdk/policy-sdk

**Nyxora Policy Engine SDK** – The rigid security middleware for the Nyxora autonomous agent framework.

@duct-sdk/sdk

Duct SDK — manifest, CLI, and embed components for permissioned human and agent access to your product APIs.

@ai-sdk/policy-opa

Policy-as-code authorization for AI SDK tool calls, powered by [Open Policy Agent](https://www.openpolicyagent.org/).

@ogxavier/argus-sdk

TypeScript SDK for the Argus multi-agent security consensus oracle on Arc

cwn-eve-trust-gate

eve (Vercel agent framework) tools for Trust Gate post-quantum, tamper-evident receipts.

@radware/openclaw-radware-agentic-protection

OpenClaw integration package for Radware Agentic AI Protection

@jin0/agentic-workflow-guard

Static analyzer and GitHub Action for detecting Agentic Workflow Injection risks in AI-powered GitHub Actions workflows.

toolgovern

Runtime governance middleware for AI agent tool calls -- gate shell, filesystem, network, and credential access before a tool executes.

correctover

Correctover - AI Agent Runtime Assurance. CCS standard + GuardrailProvider + MCP Security Scanner. Framework-agnostic runtime security for AI agents.

@intentrax/sdk

Intentrax deterministic public SDK for proof verification and API-wrapper execution.

prismor-mastra

Prismor for Mastra — policy-controlled tool calls via a wrapped execute function and the Prismor eval-server

@globiguard/sdk

Server-first TypeScript SDK for GlobiGuard control-plane and trusted decision-engine connectivity.

More in Security & AI safety