Reusable AI skills and capabilities for agent workflows
raguets
RAG extension for Pi with Qdrant, pgvector, ChromaDB and OpenAI-compatible embedding providers.
CraftedWithIntent <[email protected]>
Semantic cache + reverse proxy for LLM inference
GitHub Actions
n8n community node for Sharek — schedule and automate social media posts
GitHub Actions
n8n community node for PixelPanda — AI product photos, virtual try-on, avatars, UGC video, background removal and upscaling
...morefliu56
dsh plugin: persistent whole-machine LLM usage ledger with a pure-text /llm-stats command (tokens, cache hit, model/tool time, per-day bars)
...moreICT Innovations <[email protected]>
LangChain tools for ICTContact / ICTDialer — start, stop and monitor outbound call-center campaigns over the REST API
ICT Innovations <[email protected]>
LangChain tools for ICTExam — parse question papers with AI, publish exams, and read gradebooks and item analysis over the REST API
...moreJaret Arnold
Put one question to several LLMs independently and read every answer in full -- parallel judges, failure classes, cost, and an anonymized rebuttal round
...morefliu56
dsh plugin: SYSTEM proxy (env) + LLM traffic-splitting proxy via a process-global undici routing dispatcher
GitHub Actions
n8n node for Beehiiv API
rendofy
n8n community node for Rendofy — the unlimited render engine for n8n & Make workflows.
GitHub Actions
n8n node for Freedom24/Tradernet Trading API
GitHub Actions
HighCtrl credential and native n8n integration package.
mzzsfy
NewAPI 等 LLM 网关接入:跨协议会话粘性标记,提升网关侧 prompt 缓存命中,compat 全开放
Sunil Prakash
Content guardrails for LLM applications, with published precision and recall and provenance on every decision.
gkour
Fast.com but for LLMs — a CLI benchmark tool that races LLM providers head-to-head on tokens/sec, time-to-first-token, and total latency.
...moremorlay_null
OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.
...moreBen Houston
Browser LLM inference on WebGPU using Three.js TSL compute shaders.
hisomestudio05
n8n community node for social media scheduling — schedule posts and manage a unified inbox, media, analytics, and social accounts across 20 platforms (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Threads and more). Powered by So-me Studio.
...moreJulien LS
Traduit des fichiers Markdown avec OpenAI, Claude, Mistral, Gemini, Grok ou Codex, en préservant la mise en forme, les blocs de code et le front matter.
...moreSmejkal Design <[email protected]>
a terminal pet for your Claude Code statusline that evolves as your memory grows
kylelayer
HumanLayer's vendored OpenAI-compatible provider for Effect AI SDK
sahar-madan
Shared Pallasoft package for communicating with the OpenAI API — chat/completions, function-calling tools, and realtime voice — built on OpenAI's official `openai` library. Server-side helpers live under `OpenAI.Server`, the browser-side realtime voice ho
...moreSmartly.io
Mirage.js adapter for Oats