Search

AWS Bedrock Agents governance middleware for Aegis ACP (maintenance-only — Anthropic SDK is the active hero)

LLM/agent observability for behavior deviations, guardrails, and telemetry

TypeScript package for AppSec AI Agent management

Red-team your AI agents: a CLI that fires authorized attacks at LLM and agent targets.

Deterministic, no-LLM tool-call guardrail for Strands agents, backed by the rein engine.

Privacy shield for AI Agents: Automatically mask PII and credentials before sending to LLM APIs. Supports tool calls & streaming.AI Agent 隐私防护盾：在调用 LLM API 前自动遮罩个人身份信息和凭据。支持工具调用与流式响应。

Community Edition — AgentMesh Runtime: Execution supervisor for multi-agent sessions with privilege rings, saga orchestration, and audit trails

Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.

Autonomous reverse-engineering agent with a source-aware reverser/checker loop, objective verification, parity checks, and a Ghidra backend

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

Portless MCP server — persistent memory, local inference, and 44 tools for a personal AI agent system

AI model: golf-mcp/golf-prompt-guard

Deterministic governance guard for Pydantic AI agents — policy enforcement, PII detection, cost tracking, kill switch, and structured audit evidence. No LLM in the governance path.

Next.js middleware for AgentShield AI agent detection

Antarraksha AI Agent Enforcement SDK for Crewai

AI model: mradermacher/AgentDoG-FG-Qwen2.5-7B-i1-GGUF

Deterministic governance hook for CAMEL-AI multi-agent systems — policy enforcement, PII detection, cost tracking, kill switch, and structured audit evidence. No LLM in the governance path.

Azure AI Agents client library.

AI model: mradermacher/AgentDoG-Qwen2.5-7B-i1-GGUF

SecureVector SDK for LangChain — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangChain tool call, with tamper-evident audit logging.