Search

n8n node for Stability AI API

Marketing Architects Node for n8n

Kimi AI (Moonshot AI) n8n custom node for chat completions, multi-turn conversations, streaming, and memory management.

Sanqian AI SDK - provider-neutral AI runtime for all products

Multi-user RAG server with team access control — built on zettabrain-rag

LLM cost and usage observability SDK

Base module to allow exchanging files via storage backend (eg: SFTP).

OpenAI engine adapter for auggy — implements ModelClient against the openai SDK.

model-gear — run, assess, and switch the local vLLM model.

n8n community node for the eResource Scheduler (ERS App) API to manage resources, projects, bookings, requirements, and timesheets in n8n workflows.

LLMT: High-Performance Streaming Dataset Loader for LLM Fine-Tuning

Cisco IOS automation agent CLI with mock simulation, guardrails, and LLM tool-calling support.

OpenAI Responses API phase executor for Coro — stateless conversation replay, MCP-backed tools, and provider-owned cost accounting.

OpenAI-compatible embedder for ObjectStack — works against OpenAI, 阿里通义 DashScope, 智谱 BigModel, 硅基流动 SiliconFlow, 火山引擎 Doubao, MiniMax, Ollama, and any drop-in OpenAI-shape endpoint.

Bluerouter CLI - Start and manage Bluerouter server

Manage multiple Claude Code instances with different aliases and configurations

Two-pass LLM pipeline that turns Markdown files into a confidence-scored knowledge graph with an induced RDFS/OWL ontology

n8n community node for Hyperspell — add documents, semantic search, and AI-grounded answers from any workflow.

AI SDK v6 provider for cdecli agent running in a Kubernetes pod. Resolves the pod via kubectl, opens a port-forward, and proxies generateText / streamText calls to /v1/agent/chat.

Plan the whole system before your agent writes a line of code. Local-first planning layer with structured entities and typed relations.