Search

Local inventory of the AI agent surface on your machine. No account, no network, no upload.

Access control framework for MCP servers with Android-style permissions

EYDII Verify tools for LlamaIndex — verify every agent action before execution

SidClaw governance integration for LangChain — policy evaluation, human approval, and audit trails for AI agent tools

A least-privilege controller for local coding agents

Universal AIGP (AI Governance Protocol) client — consent-based runtime AI governance

Ferret — self-hosted outbound tunnel agent. No port forwarding, no third-party cloud.

TypeScript SDK for the Bastion trust proxy for AI agents

Autonomous red team for MCP servers. Sends adversarial payloads to your tools, proves exploitation, reports what's broken. 53 attack patterns across 6 categories. Zero dependencies. npx decoy-redteam

Antarraksha AI Agent Enforcement SDK for Openai Agents

Policy-aware AI permission reviewer for OpenCode. Evaluates tool and command requests, then allows once, denies with feedback, or escalates to the user.

A safety layer for AI agents; it decides what your agent is allowed to do - and proves it.

Model Context Protocol (MCP) server in Go for ThreatBook TDP (微步在线威胁检测平台): 105 OpenAPI endpoints + 4 diagnostics as typed MCP tools - alert triage, incident forensics, log hunting, threat intel & SOC automation.

Preflight AI coding repositories before Codex, Copilot, Cline, Claude, Gemini, Continue, or Cursor touches them.

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

The Trust Layer for AI Agents – Zero-Knowledge Handshakes between autonomous machines.

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

RAG provenance, write gating, and drift detection for AI agents — EU AI Act compliance infrastructure

AI-Powered Codebase Bug & Vulnerability Scanning CLI

面向 AI Agent 的授权网络评估工具集 — TCP 端口扫描 / DNS 子域枚举 / 目录爆破 / HTTP 指纹识别，JSON in / JSON out 并附 MCP 服务（BIT 生态）