Search

Vendor-neutral CLI for validating portable Agent Skills

CLI to evaluate agent skills triggering

Scaffold a Karpathy-style LLM knowledge-base repo for Claude Code, driven by kb-* skills.

LLM-runtime-agnostic X++ AX 2009 skill suite

Pi extension that estimates model-facing context footprint by resource.

A lightweight AI gateway that makes LLM providers OpenAI-compatible.

Version, diff, and A/B test your LLM prompts — like git for prompts.

Skills and agents for Claude Code — 11 skills + 12 agents

AI-native GitHub issue planning via GitHub issues

Run Claude Code powered by Kiro CLI — one command, zero config

Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics.

Drop-in Anthropic SDK wrapper for AgentLoop. Adds memory retrieval and turn logging to every messages.create call.

GovernMy.ai adapter for Anthropic's SDK tool-use loop — wraps Claude messages.create() with regulatory obligation checks

Helpers for the boring-but-important code around every LLM API call: prompt safety, cost budgets, structured JSON output, conversation trimming, retry, and tool schemas. Works with OpenAI, Anthropic, and Gemini. Zero runtime dependencies.

GovernMy.ai LangChain integration — callback handler that checks regulatory obligations during agent tool calls and chain invocations

Mako Security CLI - scan for vulnerabilities in dependencies, code, and infrastructure

A linter for AI behavior — catches duplicates, unregistered components, and hardcoded secrets in React projects

Perfectly Clear (eyeQ) image enhancement plugin for the CE.SDK editor

Next-generation LLM-powered auto feature engineering framework with GitHub Copilot SDK

Code mode for pi