Reusable AI skills and capabilities for agent workflows
GitHub Actions
Community Vercel AI SDK provider for Interfaze (interfaze.ai) — chat, structured output, guardrails, reasoning, and internal-task precontext on providerMetadata.
...morehank reed
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
...morefroggy1014
Unofficial n8n community node for the Gitea API. Generated from the official Gitea swagger spec and kept in sync automatically. Not affiliated with Gitea Ltd.
...moregxcafe
Scaffold a local-LLM (Ollama) app with output contracts, a human approval queue, and watchdogs pre-wired — the guardrails distilled from 8,000+ logged agent failures.
...moreMarco Montanari <[email protected]>
Ontology-first RAG: extract a governed knowledge graph from documents and serve it over SPARQL and MCP.
GitHub Actions
n8n community node for WaveSpeed AI - generate images and videos with hundreds of hosted AI models
GitHub Actions
WaveSpeed AI provider for the Vercel AI SDK
Adji Bousso Dieng
Diversity-aware retrieval for RAG: the Vendi Retrieval Score, standalone or in the Vendi-RAG loop
GitHub Actions
n8n nodes for Uptimeify: manage monitors, incidents and status pages, react to alerts, and run public network diagnostics
...morekickcall
n8n node for Kickcall AI
florian_standhartinger
Turn HTML, Markdown or a URL into a PDF and get the file back on the same node. No template editor, no template IDs, no self-hosted container.
...moremoriofsyoge
n8n node to fetch and monitor App Store and Google Play reviews in one normalized stream, powered by the App Review Monitor Actor on Apify
...moreuno-km <[email protected]>
Supply-Chain Verified GGUF Runtime, Model Manager & OpenAI Supervisor for Android Termux & ARM64
Imre Fazekas
Restate.dev helpers for LLM manipulation
GitHub Actions
E2B sandbox provider for the Vercel AI SDK
Adib
Fast ONNX-based text, image, and sparse embeddings for Python. 5-8x faster than fastembed.
GitHub Actions
A controlled workflow for agentic software development.
Jesse van de Kasteele
Local, rule-based EU AI Act risk classifier with an AI security lens (NIST AI RMF, OWASP LLM Top 10, MITRE ATLAS) and document generation.
...moreKevin Dickinson
Practical local LLM evaluation on real hardware
moeadham
Streaming speech-to-text for DeepSeek Harness using AllModels.io.
AnGIneer AI inference client library (LLM multi-model routing, retry, circuit breaker, streaming)
GitHub Actions
n8n nodes for the CogNEXUS Decision API and envelope proxy. Fail closed on HTTP 503. review does not wait inside n8n.
starefinger
DeepSeek Harness LLM adapter plugin for locally deployed Qwen models behind a vLLM OpenAI-compatible endpoint: per-model multimodal switch, fully configurable reasoning efforts, and a web settings page (client plugin) for editing the deployment from the f
...moreFarhan
LangChain retriever integration for YouTube — search videos, fetch playlists, extract transcripts, and retrieve video metadata.
...more