Reusable AI skills and capabilities for agent workflows
macrozone
Panter cli tool for cloud CI/CD and DevOps
zxlin
A wrapper for the wkhtmltopdf HTML to PDF converter using WebKit
m11ps
llama.cpp bindings for Bare
contexthound
Developer-first prompt-injection scanner for CI and local use
GitHub Actions
Three-tier memory architecture for OpenCode — distillation, not summarization
edspencer
Use MDX to render high quality LLM prompts
nathaner
Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard
GitLab CI/CD
LangChain.js integration for KServe inference services
chadananda
A lightweight, composable JavaScript framework for building LLM-powered agent flows
angan
OpenKilo - Access 40+ free AI models through Kilo Gateway. Zero-config, no API key required for free models.
GitHub Actions
LLM-based dependency detection for external resources
javajack
CLI tool to add Google Analytics, GDPR cookie consent, SEO, and LLM optimization to Astro Starlight documentation sites
kkkhs
A CLI Coding Agent inspired by Claude Code - An AI-powered coding assistant that can read, write, and execute code
willmalcs
Intelligent auto-approval hook for Claude Code using PermissionRequest
etfleming
Self-hosted AI assistant — install and run with a single command
chintan123
AI-powered CLI tool for building, maintaining, and troubleshooting Kubernetes and OpenShift clusters
protectsafe
Basic CLI tool for interacting with FSAI Platform OS
teulaert
Use Onoma as your AI model provider in OpenClaw
vainplex
Cognitive immune system — L2 semantic health checks with LLM analysis, tool exposure for agent queries, and Sitrep replacement
...morekytix
<div align="center">
fender21
Zero-setup CLI for free AI chat. Just login with Google/GitHub and start chatting - no API keys needed! Uses rotating free providers with smart caching.
...moreGitHub Actions
A Hexo plugin to translate posts using LLM (Large Language Models).
asterismono
Astro integration to automatically translate content using LLMs.
frank2006x
A lightweight, low-latency ML-powered guardrail to stop prompt injection attacks before they reach your LLM.