Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 32 of 37

solomon-llm-shield

Enterprise-grade LLM security guardrail library for protecting input prompts and output responses

steward-agent-governance

Citation-verified effective-access analysis for AI agent fleets.

stoa-agent-risk

Local-first AI agent inventory and risk scanner: finds agent candidates with evidence, maps capabilities and integrations, and gates newly introduced high-confidence critical risks.

superred-optimizer-gepa-agentic

GEPA reflective prompt evolution optimizer for superred agent targets

superred-optimizer-poisonedrag

PoisonedRAG knowledge-corruption optimizer for superred

swarm-safety-gate

Deny-by-default command safety gate and text-ReAct routing agent for small LLMs

tealtiger-semantic-kernel

Deterministic governance filter for Semantic Kernel — function-call authorization, PII scanning, cost budgets, and structured audit trail.

vaid-langchain

LangChain request-signing adapter for the VAID standard: sign every outbound agent HTTP request with a VAID proof-of-possession via a thin httpx.Auth seam.

verifiable-agent-auth-registry

Hardened single-node registry service for Agent Auth identities

verifiable-agent-auth-sdk

Python SDK for agent identity publishing, signed messaging, and registry-based verification

vouch-openai

Sign OpenAI agent tool calls with Vouch Credentials.

warden-agent-guard

Drop-in payload firewall SDK for agent services, with APA v0.1 protection proofs.

warden-agent-sdk

Client SDK for Warden — build and sign canonical Warden delegation tokens, and route agent frameworks through the Warden MCP proxy.

phronesis

Phronesis review: compare features, pricing, use cases, access model, and alternatives for this Model Context Protocol (MCP) agent in 2026. A neutral decision-assurance layer for autonomous agent actions.

@absolutejs/agent-reputation

Evidence-based scoped AI agent reputation with W3C Verifiable Credentials 2.0 adapters.

phigon-observer

Consent-based local observer for Phigon AI agent supervision.

@agentapprove/pi

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

@atbash/sdk

TypeScript SDK for Atbash — the safety layer that evaluates AI agent actions against operator-defined policies before execution.

@absolutejs/policy

Versioned provider-neutral policy lifecycle, simulation, and AuthZEN adapter for AI agent actions.

@ory/argus

Ory Argus: the core API for building authentication, authorization, and audit into AI agent harness plugins, extensions, and custom integrations

@opensecureai/agent-guard

Dependency-free static analyzer that audits LLM agent tool/function definitions (OpenAI, Anthropic, MCP) for excessive agency, code-execution & SSRF sinks, secret access, and data-exfiltration surface — mapped to the OWASP 2025 LLM Top-10. Runs in CI.

smart-approve

High-risk-only approval hook with LLM risk analysis, behavior detection, protected-path interception, and decision memory for oh-my-pi (OMP) and pi-agent.

agent-sanitizer

Defend an agent against hidden-content injection: strip payload-capable invisible Unicode and ANSI, splice out human-invisible HTML, and flag data-exfil URLs in untrusted text before any model sees it.

nexusgenesis-agent-keys

NexusGenesis Agent Autonomous Key Security — PQC (Dilithium2) keys, AES-256-GCM encryption, three-tier key derivation, and human takeover. Private keys never leave the agent/browser.

eslint-plugin-vercel-ai-security

ESLint plugin for Vercel AI SDK security — detects prompt injection, system-prompt leaks, hardcoded API keys, and unvalidated model output in generateText and streamText.

agent-boundary-check

Command-line security tool that verifies what AI coding agents can actually read, write, execute and reach using synthetic canaries.

agent-opaque-env

Self-describing encrypted env files for AI-assisted development

agentavow-agt

AgentAvow (formerly agentgraph-agt) trust provider for Microsoft Agent Governance Toolkit

agentavow-pydantic

AgentAvow (formerly agentgraph-pydantic) trust verification middleware for PydanticAI agents

agentavow-sdk

Python SDK and CLI for the AgentAvow trust and identity platform (formerly agentgraph-sdk)

agentcharter

Agent-neutral policy-engineering framework

agentgov-core

Shared invoke-boundary core for agent-governance-demo: host adapters, entitlement/policy resolution, the governance envelope, and the registry Postgres schema. Published to PyPI via OIDC Trusted Publishing (.github/workflows/publish.yml) and installed into registry-api/workflows images.

agentmetry

Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail and SIEM forwarding

agentomy-sdk

Python SDK for Agentomy AI Governance Platform

agentscan-cli

Deterministic security scanner for AI agent skills + Trusted Distribution CLI. Local, zero-dependency, executes nothing. Facts, not verdicts.

crewai-tollwarden

TollWarden payment security for CrewAI agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection via a tool-call hook, and guard payment tools so blocked payments can never execute.

das-llm

Deterministic Adversarial Simulation (DAS-LLM) Framework for LLM Security Invariants

fg-agent-id

Self-certifying agent identity: keys, addresses, did:amp, signed cards, owners, and delegation chains.

langchain-tollwarden

TollWarden payment security for LangChain/LangGraph agents: scan x402 payments before settling, auto-tag provenance for prompt-injection detection, guard payment tools so blocked payments can never execute.

llama-index-guardrails-icephi

Sub-20ms prompt injection and jailbreak protection for LlamaIndex query engines.

llm-security-gates

Practical, FOSS-backed security gates for LLM systems: model-file supply-chain gate, runtime I/O firewall proxy, and model resilience scoring.

llmsafety

AI-security auditor — score any AI endpoint against Responsible-AI metrics, plus a 44-control safety register (early/experimental)

llmsentinel

Audit trail, authorization, and anomaly detection for AI agents

q-agent-sdk

Q SDK — Instrument any AI agent with security governance

swarmauri_pop_cwt

COSE Sign1 proof-of-possession helpers for Swarmauri

vexaagentwall

Python client SDK for Vexa AgentWall AI security gateway & firewall

proofchain

ProofChain review: compare features, pricing, use cases, access model, and alternatives for this ai-security agent in 2026. Verifiable AI agent compliance with soulbound identity and tamper-evident audit trails on X1.

proofchain-kya

ProofChain KYA review: compare features, pricing, use cases, access model, and alternatives for this ai-security agent in 2026. EU AI Act Article 50 compliance audit agent with tamper-proof cryptographic seals.

claudewatermarks

ClaudeWatermarks review: compare features, pricing, use cases, access model, and alternatives for this AI Detection agent in 2026. Inspect hidden text artifacts locally in your browser.

passcontrol

Secure Agent Control Plane & Passport Vault — identity-aware reverse proxy for AI agent credentials.

agent-runtime-guard

Agent runtime rule engine: tool ACL -> dangerous pattern -> constitution immutability -> identity continuity

agent-safety-doctor

Local-first safety scanner and incident report generator for AI coding agent workspaces.

agent-tooltrust

A pre-execution, deterministic policy decision point for tool-using AI agents. Evaluate every proposed tool call against declarative policy and return allow / audit / escalate / deny.

agentforge-secure

An extensible, security-aware AI agent framework with Skills and Plugins.

agentgaurd-sdk

Zero-configuration auto-instrumentation and guardrails for multi-agent LLM frameworks.

agentshield-provenance

Provenance-aware runtime security primitives for autonomous AI agents

agentvalet

Call approved SaaS platforms from any Python agent. Your agent never holds the downstream credential.

agentvisa-gateway

AgentVisa credential presentation gateway

agentvisa-verifier

Platform-side verification library for AgentVisa v3 authentication

langchain-1claw

LangChain integration for 1Claw — HSM-backed secrets, signing, memory, and automations for AI agents

mcp-agentlock

AgentLock authorization middleware for MCP (Model Context Protocol) servers.

wai-agent-audit

Signed, tamper-evident receipts for A2A and MCP agent interactions (triple-entry accounting)

warrantor-agent

AumOS Agent SDK — unified Python SDK that gives coding agents AumOS security primitives as first-class objects

@gnt-ai/cli

Adds a company-policy check before consequential AI agent actions run.

gatra-sdk

Official TypeScript/JavaScript SDK for GATRA Zero-Trust AI Agent Security Engine

@absolutejs/webmcp

Secure WebMCP registration, policy, audit, and test adapters for browser-native AI agent actions.

guardskills

Security gate for AI agent skill installers

@radware/n8n-nodes-radware-agentic-protection

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

@lians-ai/lians

Cross-platform decision evidence and reconstruction for regulated AI agents

agent-bouncer

A policy enforcement point for agent spending: blocks transactions that violate a declarative policy and writes a tamper-evident, signed audit log of every decision.

agent-gatekeep

Agent control surface: vault-backed rollback, typed hooks, circuit breaker, audit log

agent-honesty

Execution integrity and trajectory authenticity governance middleware for autonomous AI agents

agent-security-bench

Agent Security Evaluation Kit — score agent code and refuse unsafe tools, with receipts, AST checks, and live-trace adapters.

agent-skill-registry

Git-backed registry and guardrails for shared agent skills.

agent-sql-guard

Deterministic policy engine for LLM-generated SQL: SELECT-only, PII column denylist, table allowlist, cost cap. Multi-dialect via sqlglot (BigQuery, Snowflake, Postgres, Trino, …).

agentbarrier

Transaction-safe policy, approval, and execution gateway for AI-agent actions

agentgate-firewall

Firewall for AI coding agents. Intercepts Bash/Read/Write/Edit, blocks outbound HTTP, asks humans via Slack/Telegram for risky ops. Works with Claude Code, Cursor, Continue.dev, Aider, and GitHub Actions.

agentic-security-harness

Open-source defensive harness and learning lab for reproducing and measuring agentic AI failure modes with portable traces, attack graphs, scorecards, and data-boundary tests.

agentperimeter

AgentPerimeter — runtime governance for AI agents with CIS-region compliance (FSTEC 117, GOST R 57580, KZ AI Law). Name reservation; product at agentperimeter.ru

agentproofchain

Cryptographically signed, tamper-evident audit logs for autonomous agents

agentrust-trace-adapters

Build TRACE Trust Records from evidence another system produced, without fabricating what is not there

ai-agent-guardrails

A tool-agnostic policy layer that intercepts and blocks destructive commands proposed by autonomous AI coding agents, with full audit logging.

dhms-agentfuse

Experimental fail-closed pre-dispatch boundary for AI agent tools.

llm-ffw

High-speed deterministic scanning for LLM inputs and outputs

llm-provenance-probe

GenAI model provenance and jurisdiction assurance harness

mcp-agent-guard

Runtime security proxy for MCP agent tool calls

nexusclaw-agent-governance

Governance for AI agents: deny-by-default tool gating, L0-L4 guardrails, human approvals and a full audit chain — via the agent-governance sidecar.

open-agent-contract

Vendor-neutral Governed Contracts for verifiable agent authority, constraints, conformance and consequence.

open-agent-profile

Reference validator and applicator for the Open Agent Profile (OAP) specification

openagentfence

Python interoperability utilities for OpenAgentFence security traces (early development)

parapetai-agent

Open-source in-process governance for AI agent frameworks: Cedar-governed model/tool calls via build_middleware()/GovernedAgent, plus the Cedar engine, request/decision shapes, PEP<->control-plane protocol client, and Ed25519 PEP identity they run on.

safe-agent-l

Runtime enforcement library for autonomous AI agent systems: constraint enforcement, auditable decision traces, defense-in-depth safety controls, and fail-closed network resilience.

superred-optimizer-agentvigil-websentinel

AgentVigil/WebSentinel indirect prompt-injection optimizer for superred agent targets

superred-optimizer-eia-agent

Environmental Injection Attack optimizer for SuperRed web agents

@stylusnexus/agentarmor

Open-source agent security framework. Detects and defends against AI Agent Traps - content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more.

dsh-plugin-vajraclaw

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

attestify-mcp

The only agent execution layer that enforces governance before consequences land. x402-native paid execution, financial control plane, immutable receipts, output verification, agent reputation, memory continuity, and Attestify Trust (no-wallet agent ident

@ourobx/shield

Kernel-level Zero-Trust Security SDK for AI Agents and LLMs via Agent-eBPF

@aegis-kernel/langchain

LangChain and LangGraph deterministic invariant tool guard

adapt-agent

ADAPT-Agent: Adversarial Defense & Policy Training for LLM Agents - A comprehensive library for LLM agent optimization and security

More in Security & AI safety