AI guardrails & agent security
3,625 agents · most starred first
AI guardrails & agent security, page 17 of 37
AI Agent Governance CLI — evaluate tool calls against rules, block dangerous operations, and surface blocked commands
matt — AI agent telemetry for developer machines
AI agent command firewall with Telegram-based human approval
AI agent governance SDK by Aten Security
Agent Integrity Protocol — real-time thinking block analysis for AI agent alignment
Intent DNA — Declarative policy layer for AI agent behavior
Security-first package manager for AI agent skills
Open-source CLI scanner for risky MCP server and AI agent tool configuration.
AI agent governance - audit trails, policy enforcement, ML-DSA cryptographic signatures
AI Agent Security Monitor — intercept and approve dangerous commands in real-time
Security auditing CLI for AI agent skills — OWASP Agentic Skills Top 10 (AST10)
AI agent security plugin for OpenClaw: prompt injection detection, PII sanitization, and monitoring dashboard
Local-first MCP router integrity auditor for AI agent workflows.
Security scanner for AI agent packages — CLI + MCP server
Scan AI agent skills for prompt injection and malicious code
Security scanner for AI agent tooling — MCP servers, tool definitions, and agentic pipelines
JavaScript SDK for checking AI agent actions before they run.
Scan, score, and fix AI agent configuration files
Tri-state tool permission system (allow/deny/ask) for AI agent tool invocations
CLI for LLM agent secret safety — load env secrets without exposing values
Framework-agnostic safety helpers for tool-calling LLM agent loops.
Deterministic action verification for LLM agent security
Deterministic, config-driven guardrails for LLM agent tool calls
An http(s).Agent implementation that block request Private IP address.
Local secret vault for LLM-safe environments — encrypted secrets that agents can't bulk-discover
CLI helpers for logging hardware UUIDs and posting startup payloads to Optimus Security.
CLI helpers for logging hardware UUIDs and posting startup payloads to Optimus Security.
Fully featured SOCKS proxy client supporting SOCKSv4, SOCKSv4a, and SOCKSv5. Includes Bind and Associate functionality.
A javascript port of Matomo device-detector
Agent Identity: UserPool (用户池) login, TIP token (工作负载令牌), credential hosting (凭据托管 OAuth2/API key), optional tool/skill permission control (CheckPermission) and risk approval. Integrates with Volcengine 智能体身份和权限管理平台.
Bento Guard SDK - AI-powered security infrastructure for autonomous agents
JavaScript obfuscator
AI agent security scanner and npm audit for MCP servers, Claude Code, Cursor, and Windsurf. Find prompt injection, hallucinated packages, secrets, unsafe tools, and vulnerable code.
Runtime security middleware for LLM agents — prompt injection, tool misuse, and memory poisoning defense
Trustworthy memory and security for AI agents. Memory firewall for any host that writes through it; runtime tool gates on Claude Code, OpenClaw, and Hermes.
AgentLair adapter for LangChain.js — issue per-agent AATs, attach Bearer tokens to tool calls, emit audit envelopes, and sign outbound HTTP requests with RFC 9421 / Web Bot Auth.
Governance and audit infrastructure for AI agents: charter-scoped missions, policy enforcement, human-in-the-loop approvals, tamper-evident audit chains, and EU AI Act Article 12 bundles - for money-moving and operational actions alike.
Atbash safety guard for LangChain DynamicStructuredTool
Wrap LangGraph tool nodes with OC Agent scope enforcement and emit a signed agent-action envelope per execution. Binds the action to the graph-state hash so verifiers replay the audit against the persisted graph snapshot.
TypeScript SDK for Ovrule case-file classification, guardrails, and receipt verification.
GovernMy.ai LangChain integration — callback handler that checks regulatory obligations during agent tool calls and chain invocations
Atbash safety guard for LangChain DynamicStructuredTool
Module to prevent SSRF when making requests
NeuroShield Sentry — host-level agent protection daemon. Detects and blocks malicious AI agent actions at the OS level.
Official SupraWall security integration for LangChain (TypeScript)
TypeScript SDK for Silmaril Firewall — prompt injection and jailbreak detection
Local Cedar policy enforcement and signed decision receipts for AI agent tool calls.
Open Policy Agent WebAssembly SDK
Atbash safety guard and audit nodes for LangGraph workflows
Framework-agnostic agent security gateway — protect any AI agent with Veridex security packs, regardless of framework
OpenAI Guardrails: A TypeScript framework for building safe and reliable AI systems
Cross-agent permission policy specification for AI coding agents
Cross-agent permission policy specification for AI coding agents
Cross-agent permission policy specification for AI coding agents
Cross-agent permission policy specification for AI coding agents
Runtime security SDK for AI agents — guard tool calls in 1 line
AgentLair adapter for the OpenAI Agents SDK — issue per-agent AATs, attach Bearer tokens to tool calls, emit audit envelopes, and sign outbound HTTP requests with RFC 9421 / Web Bot Auth.
Wrap OpenAI function-calling (Responses API + Chat Completions tool path) with OC Agent scope enforcement and emit a signed agent-action envelope per function invocation.
Keep your AI agents on a leash. Real-time spending limits in 3 lines of code.
SWT3 AI Witness SDK: cryptographic attestation for AI inference. 103 procedures, 52 namespaces, 7 languages, 18 profiles. EU AI Act, NIST AI RMF, CMMC, SR 11-7.
Per-key budget caps for AI agents. Local proxy enforces hard spend limits on API keys. Scans your tools, tracks costs, blocks when over budget.
Beav3r client SDK for guarding autonomous agent actions.
Action-bound, signed proof challenges for verifying fresh autonomous agent work.
x402 Payment Firewall SDK - On-chain security for autonomous agent payments on Cronos
Agent Alignment Protocol (AAP) - Verification and drift detection for AI agents
agents.txt for any repo. Tell autonomous AI agents what they're allowed to do, in 60 seconds.
Arcjet runtime security SDK — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF for JavaScript and TypeScript apps
ContentSafety Service
AI guardrails and orchestration for Directive. Prompt injection, PII detection, cost tracking, multi-agent patterns.
Atbash safety judge plugin for AutoGen-style multi-agent orchestration
Cryptographic security layer for AI agents. Ed25519 identity, signed messages, trust scoring. Works with LangChain, CrewAI, AutoGen, OpenClaw, or any agent framework.
Trust-First Agent Framework — behavioral trust, cryptographic provenance, semantic firewall. The trust kernel that agentic AI is missing.
Drop-in security wrapper for AI agents - adds authorization, verification, and audit to any agent framework
Core SDK for agentic trust systems
APort guardrails for CrewAI — task decorator / middleware
VerifiedState integration for CrewAI — cryptographic receipts for every agent assertion
AuthorityRail governance plugin for CrewAI. Wrap any CrewAI tool or task with ARES-v1 pre-execution certification.
ScopeBlind evidence wrapper for CrewAI tool calls. Automatically creates Veritas Acta receipts for every tool invocation and delegation.
HELM governance adapter for CrewAI JavaScript/TypeScript — task and tool governance
Thin CrewAI adapter for the OxDeAI universal execution guard
Verra AI governance SDK: detection pipeline (PII, jailbreak, prompt injection, policy violation) with LangChain, CrewAI, AutoGen, LlamaIndex, and Semantic Kernel integrations.
Control what your AI agents do: check every tool call against your company's FullCourtDefense policy (Monitor or Enforce).
AgentGuard TypeScript SDK with local policy contracts and compatibility HTTP/in-process adapters.
Secure runtime for AI agents. Policy-enforced tool execution, secret blocking, audit trails. Drop into OpenAI, Anthropic, LangChain, CrewAI. Zero dependencies.
Framework adapters for AriKernel — protect agents built with LangChain, CrewAI, OpenAI, and more
AI agent governance platform — static scanning + runtime interception for Claude Code, Cursor, GitHub Copilot, Codex CLI, LangChain, CrewAI, and Kiro. Blocks dangerous tool calls in real-time.
Governance receipts for AI agents — DingDawg Loop Protocol (DDLP) for safe scheduled agents with governance gates, compliant with EU AI Act Art. 12, Colorado AI Act (SB 24-205), and NIST AI RMF. Every loop execution is verified, receipted, and fail-closed
AxonFlow SDK - Add invisible AI governance to your applications in 3 lines of code
Five governance questions for your AI agent system. Identity, restraint, accountability, memory, charter. Zero dependencies.
Security-focused `SKILL.md` packs for reviewing and hardening LLM systems.
Enterprise AI agent governance framework. Hook-based enforcement, compliance packs (SOC 2, HIPAA, GDPR, PCI DSS, DORA, EU AI Act, ISO 27001), audit trails, multi-LLM adapter architecture (Claude production today; additional providers on roadmap).
Authorization middleware SDK for AI agents — powered by AgentGate
AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, supply chain worm detection, and more.
Free AI agent code hygiene checker. Scans for hardcoded LLM keys, shared credentials, and long-lived agent permissions in TypeScript, JavaScript, and Python projects.
Real-time behavioral guardrails for AI agents. Detect retry storms, circular reasoning, budget overruns, and failure spirals — as they happen.
Universal execution authorization guard (PEP boundary) for OxDeAI
AI agent safety framework — standing orders, danger maps, and stories that teach cats to land on their feet
Human approval gate for AI agent actions. Drop-in protection against prompt injection for any API key.
TypeScript SDK for HELM — fail-closed tool calling for AI agents
AI Agent Identity Protocol — Proof-of-Jurisdiction for AI agents on the GNS Protocol