Reusable AI skills and capabilities for agent workflows
alejandro-pai
Use any LLM with Google ADK TypeScript - supports AI Gateway, OpenRouter, and 100+ models
GitHub Actions
Package to integrate LLM based capabilities into any loopback4 application
nbonamy
Library to query multiple LLM providers in a consistent way
kimhongyeon
An extensible framework to automate your entire newsletter workflow. Handles data collection, LLM-based content analysis, and email generation, letting you focus on your unique domain logic.
...moregiacomo_grassetti
LLM plugin for Bowl PayloadCms plugin
typechat
TypeChat is an experimental library that makes it easy to build natural language interfaces using types.
GitHub Actions
Model and provider definitions for [LLM Gateway](https://llmgateway.io) - the unified API for all LLM providers.
rocketnew
Universal LLM SDK for JavaScript/TypeScript - OpenAI, Anthropic, Gemini, Perplexity and more
techupbusiness
Encode JSON → TOON (40-60% token savings for LLMs!)
GitHub Actions
Expose pages as .md endpoints for Astro
harshvermadr30
Production-safe JSON repair and schema validation for LLM outputs
zbigniew-sobiecki
Testing utilities for llmist - mock LLM responses and test agents
GitHub Actions
Agentic-lib Agentic Coding Systems SDK powering automated GitHub workflows.
texra-ai
80+ LLM models. Pricing, capabilities, context windows. Always current.
GitHub Actions
A CLI tool to interact with AnythingLLM from the terminal
theaiguy_
Static security analyzer for LLM applications — eslint for LLM security
GitHub Actions
CLI toolkit for developers using LLM coding agents
coms_indeed
Cross-platform streaming JSON parser for TypeScript optimized for LLM responses. Works on Node.js, Deno, Bun, browsers, and edge runtimes.
...moreGitHub Actions
A simple CLI to clone, manage, and link repositories for LLM reference
kingcaliber
AI Output Verification Toolkit — Local-first LLM safety, hallucination detection, PII redaction, prompt injection defense, and runtime monitoring. Zero telemetry. OWASP LLM Top 10 aligned.
...moremehulbirare
A semantic cache for LLM API calls using local embeddings and vector similarity
ai
CLI tool to update caniuse-lite to refresh target browsers from Browserslist config
minhlucvan
FireCrawl nodes for n8n
janbalangue
Fail-fast admission control for LLM workloads built on async-bulkhead-ts.