Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 35 of 37

trustmodel-agentcert-tag

Verify an AgentCert + TrustScore inside a Python MCP server (shadow mode, opt-in, dependency-free).

vamp-llm-probe

LLM API security auditor — prompt injection, jailbreak, ASCII smuggling, data exfiltration, OWASP LLM Top 10 mapping

veltra-agent

Deterministic guardrail, SIEM audit exporter, and subprocess firewall for autonomous AI agents

volcenginesdk-llmscan

Volcengine llmscan SDK for Python

volcenginesdk-llmshield

Volcengine llmshield SDK for Python

vt-agent-firewall

A fail-closed gateway between an AI agent and its tools: normalize, default-deny policy, human approval, append-only audit.

warrant-llm

A least-privilege controller for local coding agents

wellman

Wellmanifest unified standards runtime — policy-as-code checker for all wellmanifest standards

xagentguardpython

Python SDK for xAgentGuard AI Agent Governance and Enforcement Proxy

ygo74-agent-runtime-security

Security and authentication foundation of the ygo74 agent runtime

zanii-agents

Runtime for accountable AI agents: signed receipts for every action, human gates, injection defenses, hiring per proven task. Standard library only.

ztagent

ZTAgent: Zero Trust Security for AI Agents. Never trust an agent action. Verify before execution.

AgentID

AgentID gives AI agents their own sign-in identity. They can access supported apps without using your password or asking you to log in each time.

@doubleagent-so/agent-detector

Double Agent detection engine: classifies a browser session as human, bot or AI agent, entirely client-side.

agentgate-runtime-control

Runtime control plane and SaaS governance layer for AI agent tool execution

hush-secrets

hush — keep API keys out of AI agent chats. Vault + redacting runner + harness-agnostic MCP server.

@once-agent/mcp

MCP idempotency and AI agent retry safety for consequential writes and ambiguous timeouts.

@dorigjo/besa

Cryptographic admission and evidence for consequential AI-agent actions.

provenance-protocol

The Provenance Protocol — an open standard for AI agent identity — with offline verification, signing and attestations

noa-receipt

NOA Mandate Core — open, offline-verifiable receipts for AI-agent actions.

@mondoohq/skillcheck

AI agent skill security scanner. Detects locally installed agent skills, computes SHA-256 checksums, and queries the Mondoo AI Agent Security database for known threats.

@agent-utils/agent-guard

Security policy enforcement and auditing for supported AI agent filesystem tools.

omnodex

Security and observability for AI agent execution.

sasy-js

Policy enforcement for LLM agent tool calls, decided from each call's message ancestry

@guardbee/mcp-unbounded-consumption-auditor

MCP server that scans LLM/agent application code for Unbounded Consumption ("denial of wallet") anti-patterns from OWASP LLM Top 10 2025's LLM10 category: missing output token limits, missing timeouts on hand-rolled LLM HTTP calls, unbounded agent tool-ca

@atlasauth/pca-langchain

LangChain adapter for Proof-Carrying Authority: wrap a StructuredTool so every invocation emits a PCActn (and attaches the proof) before the tool runs.

fizzl-langchain

Safety checks for LangChain.js and LangGraph.js agents that pay: tools to check a transaction or signature before signing, a token before buying, a wallet's open approvals, and an x402 endpoint before paying it (presign-guard and x402 Doctor, paid per cal

arkah-agent-guardrails

Document mutation, read-before-write and admission policies for LangChain agents built on LangGraph.

@trustflow/langchain-middleware

LangChain.js middleware that verifies Trustflow domain signatures before parsing llms.txt context.

@costrinity/vitna

VITNA for agent code: check every tool call before it runs. Adapters for LangChain/LangGraph, the Vercel AI SDK 7, the OpenAI Agents SDK and Mastra. Calls you mark as risky wait for a person. Fails closed.

overwing

Overwing SDK: guardrails for LLM output, Atlas user-agent lookups (no key needed), Beacon agent-reachability checks, Preflight checks of a Solana transaction before an agent signs it, and Tower clearance for agents operating legacy systems. Typed client,

@scopebond/hook

See and block what Claude Code, Cursor, OpenAI Codex and GitHub Copilot do. Monitor or Block rules and a signed record for each action. Open source (Apache-2.0); works without an account.

@atlasauth/pca-openai-agents

OpenAI Agents SDK (@openai/agents) guard for PCA: guardrail + tool-execution hook so each agent tool call is proof-carrying + policy-gated.

@keydris/cli

Governed, per-session identity and brokered egress for AI agents

@devesh_mishra/agent-sentinel

100% Pure Dynamic Behavioral Intelligence Firewall, Speculative Micro-Detonation Sandbox & 1-Terminal Runtime Guard for Autonomous AI Coding Agents

@xshieldai/aegis

AEGIS / KavachOS — Agentic runtime governance: budget enforcement, DAN gate (human-in-loop), seccomp-bpf kernel enforcement, Falco anomaly detection + Agentic Control Center (cockpit page rendering all @rocketlang/* primitive events in one view, PRAMANA M

@scute/harness

Guardrails for the agents you build: permissions, verification, approvals, grounding and budgets from Scute, on the agent framework you already use.

@agenticprimitives/key-custody

Pluggable envelope encryption + signers + HMAC providers (local-AES / AWS KMS / GCP KMS / AKCS agentic-kms). Pure crypto primitives; no session lifecycle (that's in delegation).

@agenticprimitives/admission

Agentic Primitives Edge admission contracts: transport evidence, application authentication, canonical actor resolution, admission grants, and exact MCP invocation authorization. Zero runtime dependencies; admission is never authority.

proofbyte-agent-trace

AI-agent inventory and tamper-evident action-log verification: auditor-ready traceability evidence for EU AI Act Art. 12

@blocksifr/pctr

See what your AI agents can cause, route them safely, and prove what happened. Consequence preview, trust routing and signed execution receipts for AI agents.

brydge-core

BRYDGE's verification client: ask before an agent acts, then check against the destination's own records whether the work happened. The shared core every BRYDGE framework adapter is built on.

@lucidrail/sdk

Ask Lucidrail before a consequential tool call: authorize, wait for a person, report the outcome.

governed-loop

Out-of-band agent governance wrapper. Hard budget caps, eval plateau stop, contract enforcement, and cryptographic receipts.

@manymoats/governed-loop

Out-of-band agent governance wrapper. Hard budget caps, eval plateau stop, contract enforcement, and cryptographic receipts.

@metamynd/mcp-gateway

Put any MCP-based AI agent (Claude Desktop, Cursor, ChatGPT, LangGraph, ...) under MetaMynd governance without code.

@aegiscore-ai/sdk

Lightweight client SDK for AegisCore deterministic agent governance (MCP, OpenAI, LangGraph)

@immiscible/sdk

Approvals, spend limits and signed receipts for AI agents: ask before a tool pays, shares data or acts, wait for a person, settle, verify. Guards for the OpenAI Agents SDK, LangChain, LangGraph and the Vercel AI SDK; x402 and wallet payments; an LLM gatew

acgs-haystack

ACGS rule-based tool-call governance for the Haystack Agent before_tool hook

agent-access-review

User access reviews for AI agents and MCP servers, with audit evidence and OSCAL output

agent-audit-mcp

九维认知空间 Agent 审计层 MCP 插件:决策步骤→九位平衡三进制状态序列→审计报告 (Audit AI agent decisions as balanced-ternary cognitive states via MCP)

agent-auth-rs

Agent Auth RS 校验 SDK(spec 010 P1b):MCP 资源服务器侧 access token 校验 — aud 强校验、命名空间 sub_type 策略、kid 强制 alg、未知 kid 重取限流+负缓存、WWW-Authenticate 发现头。

agent-egress-guard

Local, best-effort egress observation for coding-agent sessions.

agent-env-audit

AI Agent 环境安全审计 CLI:供应链投毒 / 密钥暴露 / 端口暴露 / MCP server 一键体检

agent-evidence-admission

Check that an artifact has the digest its compliance document, SBOM or attestation names.

agent-firewall1

A runtime security and governance layer that evaluates AI-agent tool requests before they execute.

agent-framework-acgs

ACGS rule-based tool-call governance for Microsoft Agent Framework function tools, via function middleware and tool approvals

agent-nebula-platform

Pluggable secure-agent platform for Agent Nebula-compatible agents.

agent-nebula-sdk

Standards-oriented security SDK for Agent Nebula and Agent Genesis

agent-second-fuse

Independent fail-closed second fuse for AI agents: runtime guard + signed receipts + incident reports

agent-tollgate

AI control layer: per-role virtual MCPs, session taint, local content inspection

agent-tool-guardrails

Typed policy rails for agent-tool calls: a policy compiler that turns declarative requirements into executable (Type, Predicate, Evidence, Action) rails, a tamper-evident evidence store, trust-scored governance, and an MCP proxy that enforces it all with zero code changes.

agentapprovalprotocol

Put an AI agent's tool calls behind an Agent Approval Protocol (AAP) approval provider.

agentbelay

A local, deterministic firewall for AI agent tool calls: Claude Code hooks, an MCP proxy and a Python API, with replayable policies for CI

agentbuck

Python SDK for AgentBuck, a real-time trust enforcement layer for AI agents.

agentcomms-secure

Free, account-free messaging utility for agents over an untrusted public hub.

agentconfigguard

Preflight security auditor for AI-agent and MCP configuration.

agentevidtrace

Name reservation. Tamper-evident flight recorder for AI agents — audit ledgers, forensics, compliance evidence.

agentgate-security

Layered operator screening and session-hijack resistance for AI-agent platforms (alpha)

agentguard-auth

Python SDK for the AgentGuard AI Agent Authorization API

agentguard-lint

Find LLM cost risks in Python agent code - unbounded loops, quadratic history growth - and estimate what a run costs.

agentguard-linter

Static analysis for reliability, cost, and security bugs in AI agents

agentguard-oss

Open-source safety layer for AI agent tool calls: policy, risk checks, human approval and tamper-evident audit

agentic-action-authority

Exact-action operator approval with durable execution coordination and optional effect adapters

agentic-chaos-security

Security chaos engineering for AI agents and LLM applications.

agentic-platform-memory

SECURITY RESEARCH PLACEHOLDER — benign, does nothing. Coordinated vulnerability disclosure (dependency-confusion verification) via HackerOne. Not the real package.

agentinputlab

Auditable, intent-aware input intervention for LLM agents

agentltl-coding

AgentLTL rules for coding agents: the AGENTLTL.yaml language, a rule library, and a guard any harness can call.

agentscan-si

Security scanner for AI agents and MCP server configurations

agentsecrets-plugin

Zero-knowledge credential tools for AI agent frameworks

agentshield-gateway-sdk

Python client for the AgentShield Tool Security Gateway

agenttrafficcop

Python SDK for AgentTrafficCop — a runtime circuit breaker and schema shield for multi-agent systems.

ai-agent-ledger-py

An append-only, signed ledger for AI agent delegations. ARD finds agents, A2A talks to them — this records who authorised the work, within what limits, and how it ended.

ai-agentcomply

Developer-first runtime authorization SDK for AI agent tool calls. / 面向 AI Agent 工具调用的开发者优先运行时授权 SDK。

aidr-agent

Give an AI agent a verifiable AIDR identity: enroll from code, sign requests, LangChain and LlamaIndex tools.

aiyoplane-claude-agent-sdk

AEAP Composition Boundary Adapter for the Claude Agent SDK. Thin wrapper that attaches the Runtime Decision Point to agent tool invocations — especially useful for coding agents.

aiyoplane-crewai

AEAP Composition Boundary Adapter for CrewAI. Thin wrapper that attaches the Runtime Decision Point to CrewAI tool invocations.

aiyoplane-langchain

AEAP Composition Boundary Adapter for LangChain. Thin wrapper that attaches the Runtime Decision Point to LangChain tool invocations.

aiyoplane-langgraph

AEAP Composition Boundary Adapter for LangGraph. Thin wrapper that attaches the Runtime Decision Point to LangGraph node invocations.

aiyoplane-microsoft-agent-framework

AEAP Composition Boundary Adapter for the Microsoft Agent Framework. Thin wrapper that attaches the Runtime Decision Point to agent middleware and workflow execution.

aiyoplane-openai-agents

AEAP Composition Boundary Adapter for the OpenAI Agents SDK. Thin wrapper that attaches the Runtime Decision Point to agent tool invocations.

akeyless-agentcore-rta

Akeyless Agentic Runtime Authority (RTA/ARA) for AWS Bedrock AgentCore — secretless DB and cloud actions

aphasia-agentry

Aphasia Agentry - canary-proven breach and attack simulation for AI agents (OWASP LLM Top 10)

atlas-pca-agent-framework

Microsoft Agent Framework tool guard for Atlas Proof-Carrying Authority (PCA): make every tool/function call proof-carrying and policy-gated

atlas-pca-crewai

CrewAI tool guard for Atlas Proof-Carrying Authority (PCA): make every CrewAI tool call proof-carrying and policy-gated

atlas-pca-haystack

Haystack (deepset) tool guard for Atlas Proof-Carrying Authority (PCA): make every Haystack tool/ToolInvoker call proof-carrying and policy-gated

atlas-pca-langgraph

LangGraph tool/node guard for Atlas Proof-Carrying Authority (PCA): make every graph tool/node call proof-carrying and policy-gated, with interrupt()-based step-up for risky nodes

atlas-pca-pydantic-ai

Proof-Carrying Authority tool guard for Pydantic AI (verify a PCActn before each tool runs)

authyouragent

Auth Your Agent SDK: let AI agents act for a user on websites, with the user's approval on their phone.

autogen-nti

Full 5-pillar NTI post-quantum security for AutoGen and Microsoft Agent Framework.

More in Security & AI safety