A minimal, zero-dependency, AI friendly, library for runtime type checking with developer ergonomy in mind
BEM React ClassName
A tiny (367B) utility for batching and caching operations
Claude Code frontend-engineering agent framework for scaffold-nextjs-app apps (Next.js/React/MUI/Clean Architecture). Installs agents, skills, and an orchestration loop into a project's .claude/.
React useReducer with async actions
Tiny, lightweight module for encoding and decoding Base64 URLs
AI-powered autonomous coding assistant with AI test generation, multi-model support, and plugin system
Real-time server monitoring dashboard for Hono.js. Works with Node.js, Bun, and Cloudflare Workers. Express-status-monitor style metrics with polling updates.
```sh npm i @288-toolkit/sprite-animation ```
UI Components for React
VLA vision-language-action inference addon for QVAC (ggml backend)
Lightweight HTTP message relay for inter-agent communication across machines
Middy AWS Lambda event loop tracer middleware
Execute shell commands in persistent zmx sessions from pi
Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, immutable audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode
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
An AI-native terminal workbench for services, Git review, logs, and MCP workflows.
Agent cli for coding and more.
A tiny node module for parsing FormData by name into objects and arrays
It's inspired by [react-dropzone](https://github.com/react-dropzone/react-dropzone) and implemented with vue3.
Helper function to ease doing async work in a loop
OpenClaw adapter for governed agent skills and approvals.
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
Pi extensions for structured project state, workflow orchestration, and behavior monitoring — single install for all three