Search

n8n community node extending Microsoft Excel with SharePoint file support

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

LLM comparison CLI for terminal-first developers. Compare 8 providers (OpenAI, Anthropic, Google, xAI, DeepSeek, Mistral, Groq, OpenRouter) + local Ollama/LM Studio side-by-side with parallel streaming, batch eval, LLM-as-judge, hallucination detection, assertions for CI/CD.

Continuous autoresearch RL runner: LLM-driven hyperparameter and code search for fine-tuning on cloud GPUs.

Source model capabilities and pricing from OpenRouter for cost-aware development without hardcoded data tables

OpenAI-compatible custom model provider for VibeControls Agent

Focused Pi extension package for showing OpenAI Codex subscription usage in the status line.

Avanor SDK — OpenAI + Anthropic auto-instrumentation

Sync Claude Code config (~/.claude/) across machines via a private Git repo, with path remapping and per-host settings overrides.

Pinecone vector-store adapter for @absolutejs/rag

Vercel AI SDK provider for Auxen — dedicated, OpenAI-compatible LLM endpoints (https://auxen.ai).

Is for now just a wrapper of https://www.npmjs.com/package/n8n-nodes-deepseek-reasoner

> Reference Anthropic Messages-API integration for [adjudicate](../../README.md).

AI model catalogs (open-assets JSON), cost calculation, and LLM utilities

n8n community node for Excel operations (merge sheets, more coming).

AMFS integration for LangChain

n8n node for Octopus Scraping - web scraping, screenshots, PDFs, and browser automation

Custom n8n node for evaluating business rules and policies

A high-performance CLI tool to convert local data science workspaces into LLM-ready context.

Benchmark suite and community leaderboard for local LLM inference on Apple Silicon