Tool-policy evaluation for Xema agents — allow/deny rules governing tool usage.

Policies for Tool Project

Reusable Pi agent platform, project adapters, MCP/tool policy, and coding workflow harness.

Protocol-agnostic classification, risk tiers, and exact-call policy. Consumable by MCP, A2A, LangGraph, and Vercel AI tool runtimes.

Isomorphic static analyzer that extracts the executables a shell command runs (resolving wrappers, find -exec, …) and classifies each by risk, for tool-policy enforcement. Fails closed on statically-unresolvable commands.

Zero-dependency TypeScript security filter for LLM streams — redact secrets, enforce tool policy, byte and event modes.

Lobster Shell plugin for Simplaix Gateway tool policy & audit integration

An AST-based pattern checker for JavaScript.

Agent spend tracking, budget enforcement, tool policy, and anomaly detection for OpenClaw

An ACP-compatible coding agent powered by the Claude Agent SDK (TypeScript)

Parses Cache-Control and other headers. Helps building correct HTTP caches and proxies

Evaluate Content Security Policies for a wide range of bypasses and weaknesses

help secure Express/Connect apps with various HTTP headers

Parse repository URLs to extract, SCM platform, domain, user, and project information.

Official ESLint plugin for Vue.js

Safe builders for Trusted Types values

Typed tool and MCP policy normalization for agent hosts.

Parse Content Security Policy directives.

Additional ESLint rules for ESLint directive comments.

ESLint plugin about ECMAScript syntactic features.