Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 29 of 37

agentvet

AI Agent Security Scanner — detect prompt injection, tool auth bypass, data leaks

@permaegis/harness-crewai

PermAegis × CrewAI — a Task guardrail that verifies a task's output HONORS the declared want (the Zoe commit|refund seam), returning CrewAI's [valid, feedback] tuple.

@permaegis/harness-core

PermAegis agent-harness core — the two universal seams (OCap gate + Zoe verify) + Merkle receipt verifier, as a zero-dependency TypeScript client (native fetch + node:crypto).

aegis-anthropic

Anthropic tool_use governance middleware for Aegis ACP

aegis-langchain

LangChain governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

aegis-openai

OpenAI tool_calls governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

claude-parallel-orchestrator

Defensive package-name reservation notice for a potential supply-chain risk.

garrison-adapters-claude

Reserved for Garrison, Agile Defense's secure agentic AI platform. Placeholder release.

garrison-adapters-langchain

Reserved for Garrison, Agile Defense's secure agentic AI platform. Placeholder release.

haystack-vaultak

Vaultak runtime security components for Haystack pipelines

iris-security-crewai

IRIS governance for CrewAI crews — Cedar policy on every agent tool call

iris-security-langchain

IRIS governance for LangChain agents — Cedar policy on every tool call

mcp-agent-security-scanner

Security scanner for MCP (Model Context Protocol) server configurations and AI agent tool permissions.

nixtla-claude-skills-installer

Defensive package-name reservation notice for a potential supply-chain risk.

openai-omega

OpenAI SDK with OmegaEngine governance - AI safety and compliance

sm-org-agent

Client signing surface for federated AI-agent chapters — identity, canonical strings, Ed25519 signatures, headers.

agents-chain

Lightweight identity, auth, and audit layer for AI agent SDKs (OpenAI, Anthropic)

@open-policy-agent/opa

Driver to connect to Open Policy Agent (OPA) and EOPA deployments.

llm-guardrails-maintained

LLM Guard Rails - An actively maintained security toolkit for Large Language Model interactions. Features advanced sanitization, harmful language detection, data leakage prevention, and prompt injection resistance with continuous improvements and enhancements.

mcp-vulnerability-scanner

Free MCP security scanner — finds risks in your AI agent setup

@posthog/warlock

Security scanner for PostHog's agentic flows

@sanctum-runtime/sdk

Sanctum Runtime SDK — the runtime trust boundary for autonomous systems. Signed action tokens, blast-radius scoring, source-trust classification (indirect-prompt-injection defense), dual-approver + auto-escalate, policy replay, SOC2 + NIST AI RMF evidence

@dawn-ai/permissions

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

@keelstack/guard

Runtime guardrails for TypeScript AI agents — prevents duplicate tool calls, enforces per-user LLM cost budgets, and gates irreversible actions before they execute. Works with Mastra, Vercel AI SDK, LangGraph.js, and OpenAI Agents SDK.

aegis-bedrock

AWS Bedrock Agents governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

agentplane-py

Runtime policy control plane for production AI agents. Block, degrade, escalate — without a redeploy.

@highflame/overwatch

Standalone security daemon for IDE-agnostic AI agent security

@nuggetslife/langchain-nuggets

Nuggets authority middleware for LangChain.js / LangGraph.js

agent-sleuth

Prevents untrusted data from triggering consequential actions in your agent.

agentguard-lib

Production-grade safety guardrails for LLM agents — injection detection, PII redaction, tool governance

llm-promptlint

ESLint for your LLM prompts — catch prompt-injection risks, missing token limits, and prompt anti-patterns before you ship.

@auth/agent

Client SDK for the Agent Auth Protocol — agent identity, registration, and capability-based authorization

deny-sh-integrations-core

Framework-agnostic vault-entry-as-tool resolver for deny.sh. The shared security core behind every deny.sh agent-framework adapter.

@radware/openclaw-guard

OpenClaw plugin for Radware Agentic Protection

aegis-gateway-pack-llm-guard

Aegis policy pack: LLM Guard scanners (prompt injection, toxicity, secrets).

agentrust-py

AgentTrust Edge — Full Governance Platform. Policy Engine + MAD Classifier + HITL + Kill Switch.

agentsec-bench

AgentSec-Bench: a security benchmark for LLM agents and harnesses, built on Inspect AI

qarai-agent-guard

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt injection, jailbreaks, and adversarial attacks.

ibbs

IBBS review: compare features, pricing, use cases, access model, and alternatives for this AI Security agent in 2026. A security badge proving your AI agent resists prompt injection attacks.

@dinpd/ai-agent-guard

Runtime authorization guard for AI agent tool calls.

agentcanary

Tripwire security for LLM agent pipelines — honeytokens that fire when an agent acts on an injected instruction. v0.1 coming soon.

agent-seal-xyz

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

bolyra-langchain

LangChain tools for Bolyra mutual ZKP authentication and SD-JWT delegation

kragg

Agent-first guardrails framework for AI-assisted Python projects

promptgate-llm

LLM security middleware and risk analysis layer for prompt injection detection

securevector-sdk-langchain

SecureVector SDK for LangChain — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangChain tool call, with tamper-evident audit logging.

@qmilab/lodestar-runtime-core

The language-agnostic governance-gate sidecar — govern a non-MCP agent runtime (LangGraph, CrewAI, AutoGen) by remoting each native tool call through the Action Kernel over a thin NDJSON-RPC seam. The reusable spine of Lodestar's runtime-adapter epic.

bolyra-agents

OpenAI Agents SDK adapter for Bolyra -- guardrails, tool wrappers, and MCP auth

lodestar-autogen

Govern an AutoGen agent's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0027).

lodestar-crewai

Govern a CrewAI crew's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0026).

lodestar-langgraph

Govern a LangGraph agent's native tool calls with Lodestar — the thin native hook that remotes each tool call through the Lodestar Action Kernel over NDJSON-RPC (ADR-0024).

shellward

AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.

agentperms

Least-privilege permissions for AI agents and MCP tools. Record what your agent does, auto-generate a safe policy, and block dangerous tool calls before they happen.

agentshield-control-plane

AgentShield SDK — instrument AI agents and capture execution events for the AgentShield Runtime Control Plane

dfx-agentguard

Autonomous security scanner for AI agents. Detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities.

securevector-sdk-crewai

SecureVector SDK for CrewAI — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every CrewAI tool call, with tamper-evident audit logging.

securevector-sdk-langgraph

SecureVector SDK for LangGraph — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangGraph tool call, with tamper-evident audit logging.

@open-policy-agent/ucast-prisma

Interpreter for using ucast conditions with Prisma.

@auxdynamics/mastguard-agent-sdk

Runtime AI agent security SDK for MastGuard — prompt injection detection, scope enforcement, tamper-evident audit logging, and policy-based guardrails.

aegis-llm

Pluggable multi-layer LLM jailbreak defense pipeline

agentauth-receipts

AgentAuth — attested identity and verifiable execution receipts for autonomous AI agents

algovoi-agent-passport-lite

Open, content-addressed agent identity references bound into the pinned AlgoVoi substrate (agent_id + issuer + scope + validity window; L1 frozen)

mujin-agentlock

npm audit for your AI agent's extensions: inventory installed MCP servers/skills and flag known-vulnerable (OSV), abandoned, and unpinned ones in CI.

ai-agent-sentinel

Wrap AI agent tool functions with dry-run preview and user confirmation before execution

@pearldigital/p3-agentic-credential-schemas

Credential primitives for the P3 Agentic Registry — types, canonicalization, hashing, and validation

agent-safety

Idiomatic, zero-dependency, provider-agnostic Python safety layer for AI agents: least-privilege permissions, prompt/input/output guards, sandbox + SSRF guards, quotas/rate/deadline/concurrency/risk budgets, loop detection, human-in-the-loop approval, constitutional rules, action previews, honeytokens, audit/tracing, and Claude/OpenAI/Gemini/MCP tool-call integration.

agentbreaker-sdk

Inline circuit breaker for LLM agents to prevent stuck loops, budget overruns, and output bloat.

agentguard-hitl

A permission gate for AI agent tool calls. Stops dangerous actions before they execute. Safe under many concurrent agents.

agentperm

Permission policy mediator for Claude Code, Codex, OpenCode, Gemini CLI, and Kiro.

leporis-agentlint

Audit MCP server configurations for security risks

sentinel-agent-sdk

Non-blocking AI agent event logging for compliance teams

@disreguard/sig

Sign and verify prompt templates and tool definitions for AI agent security

@kenhkl/agent-gate

AI Agent data collection & security analysis gateway (TypeScript)

agent-security-lens

MCP security trust-check server for autonomous agents: safe install decisions, risk signals, controls and alternatives before installing MCPs, Skills or tools.

@proofledger/sdk

The model-independent trust layer for AI agents: verifiable identity, model provenance, tamper-evident SHA-256 audit chains, policy enforcement, and outcome verification. Framework-agnostic.

beacon-protocol-sdk

Node.js SDK for the BEACON Protocol - Agent Safety Layer

agent-seal-lite

Tamper-evident audit trail for AI agents — EU AI Act ready

agentforge-governance

Governance spine for AgentForge — identity (feat-029) and, as they land, registry / policy / audit drivers

agentlogsafe

Vendor-neutral event logging and redaction for AI agent workflows

agentpit

A guard-railed harness that keeps wild agents in check - one gate, sandboxed, reversible context.

agentwall-security

AI Agent Runtime Security Platform — runtime security and behavioral monitoring for agentic AI systems

ai-agent-shield

Defensive overlay for AI agents — 8-layer architecture with harness-agnostic adapters; ships 6 of 8 layers (1 skill_vetting, 2 sanitize, 3 structured_output, 4 bash_guard+write_guard, 6 audit, 7 config) plus adapters for Claude Code (PreToolUse) and OpenClaw (before_tool_call)

dspy-security-bench

Open mission-assurance commons for secure, authorized, and reviewable AI agents.

llm-thorn

Runtime semantic security layer for LLM-powered applications. The WAF for the AI era.

raguard-security

Deterministic security middleware for RAG applications to prevent context exfiltration via indirect prompt injection.

@kubestellar/rationguard

Detect and rebut rationalization patterns in AI agent output

@getmarrow/sdk

Governance, proof, and intelligence controls for AI agent fleets.

@lockit/cli

Local-first, AI-agent-safe developer secrets manager (CLI).

@idevsec/creduent

The official JS/TS SDK for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.

@grantex/langchain

LangChain integration for the Grantex delegated authorization protocol

@ivalt/agent-auth

Human-in-the-loop MCP server for AI agents — biometric approval with PKI-signed attestation. stdio + HTTP.

toolsafe

Lint OpenAPI specs for AI agent safety — detect risky operations, missing guards, destructive endpoints, and schema issues before exposing APIs to LLMs and agents

@agenticcontrolplane/governance

Core SDK for the Agentic Control Plane — govern any tool call from any agent framework. Delegation chain, scope intersection, budget propagation, audit log.

@vextlabs/stoa-guard

Wire ANY AI into STOA in one line. Wrap a tool/function so it is gated (prove-or-permit before it runs), permit-carrying, and receipted automatically — against the open STOA API, verifiable by anyone. From Vext Labs.

@helixid/langchain

HelixID middleware for LangChain and LangGraph — verifiable credential enforcement at agent execution boundaries with per-tool scope checking.

agent-cordon

A quarantine line for the data your LLM agent ingests: scan untrusted text and outbound actions for prompt injection and exfiltration.

agent-defender

Provider-agnostic action defender SDK for AI agents

agent-write-gate

Agent-hook safety gate for AI-written code -- blocks bidi/invisible Unicode and CJK corruption at the write boundary

agenthacker

Runtime security firewall for LLM agents — four-checkpoint scan engine, local-first with an optional hosted cloud tier

agentoracle-receipt-verify

Verifier for AgentOracle composed envelopes (RFC 8785 JCS + Ed25519). Canonicalization is byte-identical to the production Node canonicalizer.

More in Security & AI safety