Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 28 of 37

@nullbridge/sdk

NullBridge AI Agent Identity Governance SDK

agent-governance-toolkit-core

Core runtime, kernel, and trust layer for the Agent Governance Toolkit

agent-shield-int

LLM Prompt Injection Detection API — 5-layer detection (Vigil + DistilBERT + mDeBERTa + Rules + Groq)

agent-sudo-mcp

Authorization, delegation, provenance, and verifiable-audit engine for AI agents

agentaudit-client

Audit & Compliance SDK for AI Agents

agentauthlayer

Library-first authentication and authorization SDK for AI agents

ostup-agent-gate

Portable, stdlib-only guardrail for autonomous coding agents — safe continuations instead of reckless actions.

openclaw-radware-agentic-protection

OpenClaw integration package for Radware Agentic AI Protection

agent-armour

Guard LLM tool calls with rules, scoring, and audit trails.

agent-token-budget-mcp

Agent Token Budget MCP — per-session spend cap with signed budget-exhausted attestations. Twin of bft-progress-council-mcp (spend-axis vs stall-axis guardrail). By MEOK AI Labs.

agentsguard

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

mcp-agent-preflight-sec

Static preflight scanner for MCP servers and agent skills

permission-mcp

Cross-agent permission policy specification for AI coding agents

@nostr-dev-kit/ndk

NDK - Nostr Development Kit. Includes AI Guardrails to catch common mistakes during development.

agentbrake

Circuit breaker SDK for LLM agents.

agenticdome-python-sdk

Official Python SDK for AgenticDome security guardrails, DLP, tool authorization, and multi-agent delegation enforcement.

fintech-llm-guard

Eight-layer middleware guardrail pipeline for LLM-powered personal finance applications

langgraph-persuasion-guard

Provider-agnostic persuasion guard built with LangChain and LangGraph.

openclaw-plugin-agenticdome

AgenticDome security middleware and firewall plugin for OpenClaw.

@skillguard/cli

Security scanner for AI agent skill files

agentguard-kernel

Constitutional Governance Kernel for AI Agents — trust scoring, approvals, audit trail

bytedance-riskhub-agent-tools

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

llm-fact-guard

Zero-dependency LLM hallucination detection middleware with billing & dashboard — real-time fact-checking proxy for LLMs

pramagent

Alpha agent trust middleware: audit trails, safety guardrails, HITL, and tool validation

@limitrum/sdk

Policy kernel SDK for verifying autonomous AI agent actions before execution.

agentadmit

AgentAdmit SDK: user-mediated AI agent authorization for any app

agentguard-security

A safety layer that lets developers use AI coding agents at work without triggering security alerts

agentis-verify

FastAPI middleware for verifying agent requests using the Agentis identity platform

singulr-sdk-agent

Drop-in singulr agent SDK — one import protects any LLM agent via Singulr Gateway

@thsky-21/thskyshield

Runtime governance for autonomous AI agents — per-run tool allowlists, write ceilings, loop detection, step limits, and timeouts. Works with LangGraph, OpenAI Agents SDK, or any TypeScript agent framework.

agent-manifest

Agent Manifest SDK — cryptographically anchor all 10 artifacts defining an AI agent at deployment

langchain-tealtiger

Deterministic governance middleware for LangChain agents — policy enforcement, cost limits, tool allowlisting, NHI scope controls, and SARIF audit evidence. No LLM in the governance path.

rampart-llm

Policy-as-code guardrail enforcement for enterprise LLM applications

sentraguard-sdk

Python SDK and drop-in LLM guardrail for the SentraGuard backend (OpenAI / Anthropic / Gemini compatible).

llm-stream-guard

Zero-dependency TypeScript security filter for LLM streams — redact secrets, enforce tool policy, byte and event modes.

@obsidian-os/swarm-shield

Zero-trust mathematical execution compiler for AI agent swarms.

agentbelt-harness

A pluggable protective harness for conversational AI agents — drop-in OpenAI-compatible proxy that defends against jailbreaks, prompt injection, data exfiltration, and denial-of-wallet.

agentrust-trace

TRACE v0.2: hardware-attested governance records for AI agents

finagent-redteam

A red-team benchmark for AI agents in financial workflows: measures regulatory-control bypass (sanctions evasion, threshold structuring, dual-approval defeat) and the efficacy of guardrails that try to stop it.

tealtiger-haystack

Deterministic governance component for Haystack pipelines — policy enforcement, PII detection, cost tracking, and structured audit evidence. No LLM in the governance path.

@agenticprimitives/tool-policy

Protocol-agnostic classification, risk tiers, and exact-call policy. Consumable by MCP, A2A, LangGraph, and Vercel AI tool runtimes.

agentvisa-fastapi

FastAPI middleware for AgentVisa AI agent verification

anthropic-ledgerproof

LedgerProof adapter for the Anthropic Python SDK. Side-channel transparency receipts for EU AI Act Article 50.

n8n-nodes-radware-agentic-protection

n8n community node for Radware Agentic AI Protection in-path enforcement

agenttrustid

AgentTrust ID SDK — runtime authorization, opaque agent tokens, and Guardian checks for AI agents

zerotrust-agents-sdk

Official Python SDK for ZeroTrust Agents Control Plane API

attestify-os

The only agent execution layer that enforces governance before consequences land. x402-native paid execution, financial control plane, immutable receipts, output verification, EIP-712 portable reputation credentials, escrow settlement, RAG semantic memory

a2a-trustgate

A2A TrustGate CLI — Safety, compliance, and governance for AI agents. Screen every action before it executes.

agent-guard-iam

IAM for AI agents — permission and access control framework

agentaudits

Cryptographic receipts for every AI agent action. Hash-chained, tamper-evident, regulator-ready.

agentbrake-sdk

The emergency brake for multi-agent systems. Stop runaway LangChain & CrewAI agents in real time, before 50 cents becomes $47,000.

agentcap-guard

Provider-agnostic hard dollar budgets + loop detection for AI agent runs. Stops the spend before it happens.

agentledger-llm

Action-time proof and delegation verification for MCP agents

cohere-ledgerproof

LedgerProof adapter for the Cohere Python SDK. Side-channel transparency receipts for EU AI Act Article 50.

haystack-ledgerproof

LedgerProof adapter for Haystack 2.x — side-channel cryptographic receipts for EU AI Act Article 50 transparency.

mistral-ledgerproof

LedgerProof adapter for the Mistral Python SDK. Side-channel transparency receipts for EU AI Act Article 50.

rag-agent-audit

CI security regression testing for RAG apps and AI agents

sentraguard-agent

SentraGuard framework-neutral guardrail core for AI agents — LangChain/LangGraph, LiteLLM, and direct provider adapters (no OpenTelemetry dependency).

@datacules/agent-identity

Provider-agnostic credential routing and identity management for AI agents

ai-sdk-guardrails

Input and output guardrails middleware for Vercel AI SDK.

lynx-agent

Policy-gated, durable, audited execution for AI agent tool calls. Every action gets a five-verdict policy check, a crash-safe checkpoint, and a tamper-evident audit event — a library, not a server.

x402-agent-suite-preflight

Drop-in preflight guard for AI agents — one call to the x402 Trust Layer (guard + security grade + attestation) before any paid x402_fetch. Works with any agent framework (LangChain, CrewAI, Coinbase AgentKit).

ai-execution-protocol

Framework instalavel para agentes de IA que reduz contexto, roteia risco, valida entregas e registra evidencias, traces e limites; gates de ferramentas funcionam quando runner, MCP, gateway, hook, CI ou host os chama.

agent-action-capsule

Reference verifier for the Agent Action Capsule SCITT profile (draft-mih-scitt-agent-action-capsule), with the typed Capsule carriers and their sealing boundary Capsule.seal(), and the anchor client.

agent-action-capsule-verifier

Verifier for Agent Action Capsules — a SCITT application profile for verifiable agent actions (name claim; implementation to follow).

agentguard-governance

Governance layer for autonomous AI agents — pre-flight checks, runtime monitoring, and post-session reporting.

agentmoat

Enforcement and audit layer for AI agents — argument-level tool firewall, trust scoring, tamper-evident audit log, and prompt-injection detection across the Anthropic & OpenAI SDKs, LangGraph, and MCP.

agentprobe-injection

Harness for measuring LLM agent resistance to indirect prompt injection and comparing defense effectiveness.

anthropic-omega

Anthropic Claude SDK with OmegaEngine governance - AI safety and compliance

autogen-omega

OmegaEngine governance integration for autogen-omega

cohere-omega

OmegaEngine governance integration for cohere-omega

figuard-langchain

FiGuard pre-flight spend authorization for LangChain agents

idprova-agents

Verifiable, scope-gated tool execution for AI agent frameworks (IDProva)

agent-passport-standard

Agent Passport Standard (APS) — Python SDK

agentsweep

Find and redact secrets in AI coding agent histories (Claude Code, and more).

argusllm-sentinel

Lightweight LLM API security layer — deterministic, no AI, no DB.

deny-sh-langchain

Wrap a deny.sh vault entry as a LangChain v1 tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

deny-sh-openai-agents

Wrap a deny.sh vault entry as an OpenAI Agents SDK tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

dome-langchain

Dome Platform LangChain adapter — govern LangChain tools with Dome authorization

dspy-omega

OmegaEngine governance integration for dspy-omega

gemini-omega

Google Gemini SDK with OmegaEngine governance

kyvvu-claude

Kyvvu compliance integration for Claude Code — policy enforcement via hooks

langchain-emilia

EMILIA Protocol guard for LangChain tools: a named human approves the exact irreversible action (Face ID / passkey) before it executes — fail-closed, with offline-verifiable Trust Receipts.

langchain-omega

LangChain integration with OmegaEngine governance - callbacks, tools, and safety chains

llama-index-tools-mint

llama-index tools MINT Protocol integration

mint-semantic-kernel

MINT Protocol plugin for Microsoft Semantic Kernel — universal work attestation for AI agents.

tenuo-claude-code

Tenuo governance for Claude Code — warrants, hooks, MCP proxy, and Cloud lifecycle

veragent

Vendor-neutral control plane for AI agents — governance, audit, and runtime enforcement.

warrantd-openai-agents

Earned autonomy for the OpenAI Agents SDK — warrantd drives the approval switch.

@blamejs/exceptd-skills

AI security skills grounded in mid-2026 threat reality, not stale framework documentation. 51 skills, 11 catalogs (439 CVEs / 177 CWEs / 805 ATT&CK + ICS / 170 ATLAS / 468 D3FEND / 8888 RFCs), 35 jurisdictions, 10-class catalog gap detector + budget gate,

pando-ai

AI coding firewall for Codex and Claude Code

@vercel/connect

SDK for obtaining scoped tokens for third-party services on behalf of apps or users. Authenticates the calling Vercel project via [`@vercel/oidc`](https://www.npmjs.com/package/@vercel/oidc) and exchanges the OIDC token for a Vercel Connect-issued credent

agentguard-enforce

Pre-execution budget enforcement for agentic AI workflows

iris-security-anthropic

IRIS governance for Anthropic Claude — Cedar policy on every API call

iris-security-gemini

IRIS governance for Google Gemini via google-genai

iris-security-openai

IRIS governance for OpenAI — Cedar policy on every API call

llama-index-postprocessor-bastion-guardrail

llama-index Bastion Prompt Protection guardrail integration

agent-authority

Authorization for AI agents: verifiable, scoped, revocable capability tokens (mandates) with attenuable delegation, for MCP and A2A. The reference implementation of agent authority — zero-dependency TypeScript & Python.

agent-safeguard

A runtime and definition-time security guardrail framework for AI agents and developers.

agentmesh-proxy

Governance proxy for every AI tool — PII/PHI masking, prompt injection detection, anomaly alerts, semantic cache, token quotas, vendor routing, compliance reports

More in Security & AI safety