AI guardrails & agent security
3,625 agents · most starred first
AI guardrails & agent security, page 19 of 37
Official Python SDK for Agent OnBoard — the identity and trust network for AI agents.
Open-source agent operations SDK — integration discovery, security scanning, autonomy rules, HITL primitives, and capability management for Python agentic systems.
Python SDK for the Agent Passport System. Identity, delegation, governance, attribution, mutual authentication, evidentiary type safety, accountability receipts, Cognitive Attestation, Instruction Provenance. Byte parity with the TypeScript SDK.
Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.
Deterministic, capability-based policy enforcement runtime for AI agents
Policy enforcement and taint tracking for AI agent tool calls.
Compliance & guardrails for AI agents — PII filtering, audit logging, GDPR/AI Act checks, kill switch
Agent Policy Layer - Portable, composable policies for AI agents
Preview and validate AI agent actions before execution.
Agent-level adversarial resilience testing. Tests what others don't: tool interactions, memory poisoning, confused deputy, cost bombs.
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool arguments, A2A payloads for OWASP LLM01 prompt injection BEFORE they reach a downstream agent. Curated from OWASP + academia + production incidents.
put your agents on guardrails
Role-Based Access Control for AI Agents with ML-Powered Anomaly Detection
Python SDK for the Agent Receipts protocol
Registri identity — Ed25519 keypairs, certificates, and cryptographic verification
A layered protocol and reference implementation for codifying risk in autonomous agent actions.
Enterprise policy, identity, approval, audit, observability, adapters, and realized-ROI controls for agentic workflows
Python SDK for agent input scanning, tool-call guardrails, and audit logs
A governance and policy enforcement layer for AI agents and non-human identities
SPL (Safe Policy Lisp) evaluator for Agent-Safe capability tokens. 150 lines, zero deps, microseconds.
Safeguards for custom agents.
Battle-hardened safety wrapper for AI agents
Production-grade safety boundaries for AI agents - policies, tracing, replay, and human-in-the-loop approval
One-line safety middleware for AI agent APIs. Prompt injection scanning, cost budgets, decision audit trails. Works with FastAPI, Flask, and any ASGI/WSGI framework.
Risk-focused diffs for agent manifests, MCP configs, and tool permission snapshots.
661 security tests for AI agent systems - MCP, A2A, L402, x402, UCP/ACP merchant-journey, AP2 mandate + Fireblocks x402 hardening + Visa TAP / Mastercard Agentic Tokens + denial-of-settlement finality, decision governance, AIUC-1 compliance, NIST AI 800-2 aligned
Security auditing tool for LLM agents, RAG pipelines, and agent frameworks
Agent-Signature HTTP header reference (x-agent-trust scheme). Canonical: x-agent-trust.
A Python package for signing agent setups
Evaluate agent skills before you install them. Think 'npm audit' for SKILL.md files.
Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.
Fail-open wrap for live MCP and personal-agent traffic on AgentStatus.
Double-signed receipts for AI-agent tool invocations — DSSE + JCS + Ed25519, verifiable offline (Python port of @p-vbordei/agent-toolprint)
LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning
Python SDK for AI agent security - threat detection, content scanning, trust verification, and red team testing
Complete Agent Trust Stack — one install for provenance, reputation, agreements, accountability, lifecycle, discovery, and economics
Hosted trust services for AI agents — CoC Bitcoin anchoring and ATHP mutual verification
Trust telemetry middleware for inter-agent communication — makes instruction contamination observable across traces
Zero-trust credential manager for AI agents — Python SDK
Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.
Public Preview — Unified installer and runtime policy enforcement for the Agent Governance Toolkit
Public Preview — A kernel architecture for governing autonomous AI agents with Nexus Trust Exchange
Runtime compliance evidence for AI agents — one-line SDK, tamper-proof audit trail, multi-framework attestation
Advanced policy enforcement layer for AI agents with 3-stage validation, transaction simulation, and security controls
Local-first runtime controls for Python LLM apps and agents: budget circuit breakers, PII/secrets redaction, tool-call policy checks, rate limits, and audit traces — in 2 lines, no hosted proxy.
Comprehensive security framework for agentic AI applications — 8-layer defense-in-depth.
Compliance, governance & observability layer for AI agents
On-chain EU AI Act compliance SDK for AI agents — immutable audit logs, KYA registration, incident reporting, post-market monitoring.
A scalable, framework-agnostic Python authentication library with JWT token management and password reset functionality
Python SDK for AgentAuth - Authorization layer for AI agent purchases with billing support
Reserved project name for future AgentAuth Core.
AI Agent session management SDK
Reserved project name for future AgentAuth SDK.
Verify AI agent identity and reputation before interacting with them.
Python SDK for AgentBouncr — Governance for AI Agents
Open spec and conformance suite for proving AI-initiated production actions
Compliance black box for AI agents - RBI FREE-AI, PMLA 2002, and KYC compliance monitoring
Bitcoin-anchored identity certificates for AI agents
Record what your AI agent is allowed to do
CI/CD guardrails for AI agents - prevent payment duplicates and data destruction
Agent Credit Bureau — trust scoring and audit reports for AI agents and MCP servers
Symmetric encryption using the ssh-agent
Institutional control layer for AI agent actions — authority, policy, risk, and audit before execution.
Cryptographic proof that a human stands behind an AI agent.
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
Core code for AgentDojo
Python Agent SDK for AgentDoor - headless agent authentication
FastAPI adapter for AgentDoor - agent authentication middleware
The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.
The open source SDK for AI agents Identity.
Runtime firewall for AI agents.
LLM Guard scanners for AgentForge guardrails
Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents
Runtime security for autonomous AI agents
Runtime authorization for autonomous AI agents, with receipts an auditor can verify offline
Action-level firewall for AI agents — intercepts tool calls before execution.
The reliability layer for AI agents taking consequential actions
The security gateway for AI agents — auth, rate limiting, and policy enforcement in one line.
Compliance-as-code middleware for agentic AI workflows.
AgentGraph trust provider for Microsoft Agent Governance Toolkit
AgentGraph trust verification middleware for PydanticAI agents
Python SDK for AgentGuard — secure API calls for AI agents
EU AI Act compliance middleware for AI agents. Make any LLM-powered agent legally deployable in Europe with 3 lines of code.
Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach. Python port of @mukundakatta/agentguard.
AgentGuard security monitoring plugin for Hermes Agent
AgentGuard security monitoring plugin for Hermes Agent
Python SDK for AgentGuard Pro - AI governance and compliance platform
Monitor and protect yourself with AI agent budget controls, approval workflows, and anomaly detection.
Runtime security firewall for LangChain agents — intercepts tool calls, enforces YAML policy, logs to SQLite.
⚠️ DEPRECATED: This package has been renamed to tealtiger. Install tealtiger instead.
AgentGuard for Hermes Agent: local spend caps, tool guards, sub-agent limits and signed decisions.
AgentGuard Python compatibility SDK for HTTP policy evaluation and integration adapters.
Python SDK for AgentGuard - AI Agent governance and monitoring platform
Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn
Compliance infrastructure for AI agents — runtime monitoring, audit trails, guardrails.
Python SDK for AgentGuard — the firewall for AI agents
Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.
Production-grade guardrails for AI agent function calls. Prevent overspending, unauthorized purchases, unsafe deletions, and more — with Human-in-the-Loop approval.
A runtime governance layer that enforces hard behavioral bounds in autonomous agents.
Streaming validation shield for AI agents