CruxHive — team AI knowledge governance layer
Governance primitives for AI-assisted compliance systems: fail-closed HITL (human-in-the-loop) gate and SHA-256 hash-chained provenance records. Framework-agnostic, zero runtime deps beyond zod. (The disclosure-card schema lives in the sibling package @pr
OpenClaw adapter for governed agent skills and approvals.
Nuxt collects anonymous telemetry data about general usage. This helps us to accurately gauge Nuxt feature usage and customization across all our users.
Bandwidth webrtc sdk
It's inspired by [react-dropzone](https://github.com/react-dropzone/react-dropzone) and implemented with vue3.
CDK Toolkit for use with LocalStack
Score the codebase for Single Responsibility violations, snapshot the initial scoring, pause for the human to pick one to tackle, refactor it in a bounded loop (re-scoring after every pass), do a multi-agent code review, and finish with a before-vs-after
A simple CLI tool for ensuring that a given node script runs continuously (i.e. forever)
Cursor-style debug agent for OpenCode — inject probes into CLI and browser apps, capture runtime data via HTTP, analyze and fix bugs automatically.
Abstract multi-provider Agent Chatham CLI
Pi extensions for structured project state, workflow orchestration, and behavior monitoring — single install for all three
launch iOS apps into the iOS Simulator from the command line (Xcode 8.0+)
Import with sanity.
Parser to convert mhchem syntax to LaTeX syntax, for downstream inclusion in MathJax, KaTeX and similar projects.
Task-driven auto-execution loop plugin for OpenCode
Implementation of Prototypejs in Node.js
Opinionated Pi package with web search, review workflows, sandboxing, memory, usage reporting, skills, and a theme
[](https://circleci.com/gh/mycodeself/mongo-migrate-ts)
Generate documentation markdown files from VueJs components using the vue-docgen-api.
agentic coding in 30 loc. a loop, two tools, and an llm.
An accessible polyfill for `[input type='time']` elements modeled after the Chrome & Firefox desktop implementations.
Browser QA your agent will actually run. Discovers every feature in a running app, exercises each one with Playwright, and reports pass/fail with screenshots so the agent can iterate to green. Installs as a skill for Claude Code, Codex, Cursor, and Copilo
TypeScript SDK for Sentience AI Agent Browser Automation