🎩 You're Invited:Meet the Socket team at Black Hat in Las Vegas, August 3-6.RSVP
Sign In
t

tyox-all

npm

11

total weekly downloads

Packages

Current Co-maintainers

Former Co-maintainers

18 packages

@weave_protocol/adapter-antigravity

Weave Protocol adapter for Google Antigravity - enforces WARD.md policies via Antigravity's PreToolUse hook system

@weave_protocol/adapter-claudecode

Weave Protocol adapter for Claude Code - enforces WARD.md policies via Claude Code's hook system

@weave_protocol/adapter-msaf

Weave Protocol adapter for Microsoft Agent Framework - enforces WARD.md policies via the MSAF middleware pipeline

@weave_protocol/adversary

Offensive engine for AI agent security testing. 68 documented + novel attacks across 5 categories. Real-browser target via Playwright. Test engine for AgentSecBench.

@weave_protocol/agentsecbench

Standardized, versioned, citable AI agent security benchmark. Curated attack suites built on @weave_protocol/adversary. Produces paste-ready reports and side-by-side comparisons.

@weave_protocol/api

Universal REST API for Weave Protocol Security Suite - works with OpenAI, Gemini, LangChain, and any HTTP client

@weave_protocol/browser

Weave Protocol browser-agent security — enforces WARD.md policies and detects indirect prompt injection (IPI) for Playwright, Puppeteer, and Stagehand-based AI agents

@weave_protocol/cli

The weave CLI - one command to set up, audit, and run Weave Protocol security for AI agent projects

@weave_protocol/domere

The Judge Protocol - Thread identity, intent verification, and blockchain anchoring

@weave_protocol/full

The complete Weave Protocol security suite for AI agents - 13 packages covering policy (WARD.md), enforcement (4 harness adapters), scanning, encryption, compliance, consensus, supply chain, and observability

@weave_protocol/hord

The Vault Protocol - Cryptographic containment and capability management for AI agents

@weave_protocol/hundredmen

Real-time MCP security proxy - intercepts, scans, and gates AI agent tool calls. Now with WARD.md policy enforcement.

@weave_protocol/inspector

Real-time MCP security proxy - intercepts, scans, and gates AI agent tool calls

@weave_protocol/langchain

LangChain.js security integration for Weave Protocol - callbacks, tool wrappers, and retriever guards

@weave_protocol/mund

The Guardian Protocol - MCP-based security monitoring for agentic AI systems

@weave_protocol/tollere

Supply chain security for AI-generated code - scans packages, Docker images, and IDE extensions (VS Code, Cursor, JetBrains) before install for typosquats, CVEs, sandwich-pattern attacks, and Docker tag overwriting

@weave_protocol/ward

WARD.md — the agent security policy standard. Define what your agents can and cannot do, version-controlled alongside AGENTS.md and SKILL.md.

@weave_protocol/witan

Council Protocol - Multi-agent consensus, communication, and governance for AI systems