Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 23 of 37

langchain-agentlock

AgentLock authorization middleware for LangChain tool calls.

langchain-agentmesh

AgentMesh trust layer integration for LangChain - cryptographic identity and trust-gated tool execution

langchain-agentoath

AgentOath trust protocol integration for LangChain -- automatic trust receipts for chains, tools, and LLM calls.

langchain-agentoracle

LangChain integration for AgentOracle — trust verification tools for AI agents

langchain-agentra

LangChain integration for Agentra — identity oracle and trust layer for autonomous AI agent transactions.

langchain-ai-identity

Secure your LangChain agents with per-agent identity, policy enforcement, and tamper-proof audit logs.

langchain-amorce

Secure LangChain agents with Amorce (Ed25519 + HITL + A2A)

langchain-arcgate

Arc Gate prompt injection detection for LangChain

langchain-auth

LangChain Auth SDK for OAuth and tool authentication

langchain-capiscio

Trust enforcement adapter for LangChain and LangGraph — powered by CapiscIO

langchain-cisco-aidefense

Cisco AI Defense middleware for LangChain agents — runtime security inspection of LLM inputs/outputs and tool/MCP calls

langchain-deepkeep

DeepKeep AI Firewall middleware integration for LangChain

langchain-deepsigma

LangChain integration for Σ OVERWATCH — governed, auditable LangChain chains and agents

langchain-edon

EDON governance for LangChain agents — govern, audit, and enforce every tool call

langchain-enigmagent

LangChain integration for EnigmAgent — resolve {{PLACEHOLDER}} secrets at the LLM boundary so models never see real API keys

langchain-eydii

EYDII Verify middleware for LangGraph/LangChain — verify every tool call before execution

langchain-forcefield

LangChain integration for ForceField AI security -- scan prompts and moderate outputs in your LangChain pipeline.

langchain-forge

Forge Verify + Execute middleware for LangGraph/LangChain — verify tool calls and track executions with cryptographic receipts

langchain-guardrails

Langchain implementation for Guardrails: Nemo

langchain-kavachos

KavachOS DAN gate callback for LangChain agents — pre-execution governance via AEGIS

langchain-kerq

LangChain integration for Kerq trust scoring and telemetry

langchain-kredo

LangChain integration for the Kredo agent attestation protocol

langchain-kya

KYA (Know Your Agent) identity verification for LangChain agents

langchain-ledgerproof

LedgerProof adapter for LangChain and LangGraph. Emits EU AI Act Article 50 transparency receipts as a side channel.

langchain-mcp-trust-gate

Trust-gated MCP tool calls for LangChain via Dominion Observatory

langchain-mcps

MCPS (MCP Secure) integration for LangChain -- cryptographic identity and trust verification for AI agents.

langchain-mcpsecure

5-layer security framework for AI agents: identity, capabilities, audit, time-bound permissions, and delegation chains.

langchain-nobulex

LangChain compliance middleware with hash-chained audit trails for EU AI Act readiness

langchain-nuggets

Nuggets authority middleware for LangChain / LangGraph

langchain-openterms

OpenTerms adapter for LangChain — sign and emit ORS v0.1 receipts for every tool call.

langchain-pangea

LangChain integrations for Pangea

langchain-permit

Access control tools and retrievers for LangChain.

langchain-plainid

LangChain integration for PlainID authorization

langchain-pqs

LangChain integration for PQS (Protocol Quality Standard) — Certificate Authority for AI agent economy

langchain-senthex

LangChain provider for Senthex Proxy — EU-hosted AI firewall with parallel runtime shields.

langchain-sidclaw

SidClaw governance integration for LangChain — policy evaluation, human approval, and audit trails for AI agent tools

langchain-spicedb

SpiceDB authorization for LangChain RAG pipelines and agents - fine-grained access control for AI applications

langchain-suprawall

Official SupraWall security integration for LangChain Python

langchain-tool-guard

Per-tool input validation and output-boundary policies for LangChain agents.

langchain-trust-gate

LangChain tool for behavioral trust scoring via Dominion Observatory

langchain-truthvouch

LangChain integration for TruthVouch Trust API — hallucination detection and content verification

langchain-urlcheck

LangChain tool that lets agents verify URL safety before navigation via URLCheck MCP server

langchain-vaultak

Vaultak runtime security callback handler for LangChain agents

langchain-zt

ZeroTrustedAI library

langevals-openai

LangEvals OpenAI moderation evaluator for LLM outputs.

langgraph-guard

This package is required for integrating your Langchain based Agentic Application to Aryaka's AISecure Guard Service.

langgraph-plainid

LangGraph integration for PlainID authorization

latch-agent

Universal gating and audit layer for AI agents — policy-based tool gating with WebAuthn approval flows

ledger_agent

Using Ledger as hardware SSH/GPG agent

lelu-agent-auth-sdk

Python SDK for Lelu — framework-agnostic authorization engine for AI agents with confidence-aware controls, Docker deployment, and human-in-the-loop workflows

lib-agent

Using OnlyKey as hardware SSH and GPG agent

libagent

Using hardware wallets as SSH/GPG/age agent

liboidcagent

A python library for requesting OpenID Connect access tokens from oidc-agent.

license-agent-client

Dependency-free Python client for a local license-agent, with optional FastAPI enforcement helpers.

lifeguard-openai

Lifeguard integration with OpenAI

light-vllm-ascend-security

Model encryption and authorization extension for vLLM 0.17.0+ on Ascend NPU

light-vllm-security

Model encryption and authorization extension for vLLM 0.18.0+

lightr-vllm-core

Core encryption and license components for vLLM model security

llama-index-auth0-ai

Placeholder package to prevent dependency confusion attacks

llama-index-callbacks-hdp

HDP (Human Delegation Provenance) — cryptographic authorization provenance for LlamaIndex agents

llama-index-callbacks-vaultak

Vaultak runtime security callback handler for LlamaIndex agents

llama-index-forcefield

LlamaIndex integration for ForceField AI security -- scan prompts and moderate outputs in your LlamaIndex pipeline.

llama-index-output-parsers-guardrails

llama-index output_parsers guardrails integration

llama-index-packs-llama-guard-moderator

llama-index packs llama_guard_moderator integration

llama-index-packs-zenguard

llama-index packs zenguard integration

llama-index-packs-zenguard-guardrails

llama-index packs zenguard guardrails integration

llama-index-tools-asimov

llama-index tools ASIMOV integration

llama-index-tools-enigmagent

LlamaIndex tools integration for EnigmAgent — resolve {{PLACEHOLDER}} secrets at the LLM boundary so models never see real API keys

llama-index-tools-eydii

EYDII Verify tools for LlamaIndex — verify every agent action before execution

llama-index-tools-forge

Forge Verify + Execute tools for LlamaIndex — verify agent actions and track executions with cryptographic receipts

llama-index-trustguard

TrustGuard integration for LlamaIndex - protect your RAG pipeline from malicious content

llama-index-truthvouch

LlamaIndex integration for TruthVouch Trust API — hallucination detection and content verification

llama-stack-provider-trustyai-fms

Remote safety provider for Llama Stack integrating FMS Guardrails Orchestrator and community detectors

llamafirewall

LlamaFirewall is a framework designed to detect and mitigate AI centric security risks, supporting multiple layers of inputs and outputs, such as typical LLM chat and more advanced multi-step agentic operations. It consists of a set of scanners for different security risks.

llamator

Framework for testing vulnerabilities of GenAI systems.

llamaverify

A package for dehallucinating LLM outputs.

llm-agent-protector

Polymorphic Prompt Assembler to protect LLM agents from prompt injection and prompt leak

llm-antibodies

Antibodies for LLM hallucinations

llm-attestation

LLM Attestation → This package is now `aiir`. Install: pip install aiir

llm-authz-audit

Static security analyzer for LLM applications — eslint for LLM security

llm-compliance-comparison-mcp

Llm Compliance Comparison tools for AI agents. Capabilities: compare providers, recommend for use case, provider risk profile. Built by MEOK AI Labs.

llm-content-filter

A simple and customizable content filter for LLMs

llm-fingerprinter

Black-box LLM fingerprinting system for model identification

llm-guard

LLM-Guard is a comprehensive tool designed to fortify the security of Large Language Models (LLMs). By offering sanitization, detection of harmful language, prevention of data leakage, and resistance against prompt injection attacks, LLM-Guard ensures that your interactions with LLMs remain safe and secure.

llm-guard-kit

v0.66.0: sycophancy_score() direction corrected — AUROC 0.9296 [0.8754, 0.9703] on Perez 2022 (was 0.0704, wrong direction). AgentShield judge_risk field fix.

llm-guard-python

LLM Guard — PII 탐지 및 프롬프트 인젝션 차단 라이브러리

llm-guardrail

AI safety guardrail — intent analysis, prompt injection detection, and policy enforcement for LLM applications

llm-guardrails

A package for LLM guardrails

llm-injection-guard

Drop-in prompt injection defense for LLM apps and AI agents — detect, sanitize, block, and audit injection attacks in real time. Includes multi-turn session scanning, allow-lists, rate-abuse detection, multi-layer scanner, FastAPI and Flask middleware.

llm-input-hardening

Deterministic Unicode-aware input hardening for LLM applications.

llm-input-sanitizer

A package for sanitizing and securing user inputs to LLMs

llm-integrity

LLM Integrity → This package is now `aiir`. Install: pip install aiir

llm-medical-guard

Guardrails for LLM-generated medical and health content

llm-obfuscator

A tool for obfuscating text by manipulating token IDs while preserving token count and structure

llm-output-guard

Validate LLM outputs against schemas with automatic retry and JSON extraction.

llm-output-sanitizer-py

Sanitize LLM outputs before HTML, SQL, shell, or markdown sinks. Python port of @mukundakatta/llm-output-sanitizer.

llm-pentest

Security testing toolkit for LLM-based systems

llm-prompt-shield

Lightweight prompt injection detection and blocking

llm-promptguard

Reliable, structured, production-safe LLM outputs with schema validation and auto-repair

llm-sanitizer

CLI + MCP server for detecting, classifying, and redacting embedded LLM agent instructions in documents, source code, and web pages.

More in Security & AI safety