Search

Composable building blocks for production RAG pipelines, with an auto-tuning evaluation suite.

A community n8n node for ntfy.sh

OpenCode plugin for ChatGPT web /backend-api/f/conversation (SSE).

A small example package

Premium AI orchestration nodes for n8n

eve extension that gives agents a full browser automation tool set backed by agent-browser

GlobalGPT 官方终端客户端（对话 TUI / 图片视频生成 / exec）

Spec-Driven Development for React — one TOML spec compiles to a red Vitest + React Testing Library suite plus an implementation brief.

Open AI API compatiable LLM server for Amlogic Device

Put an OpenAI Realtime voice agent on Microsoft Teams calls. Terminates the StandIn media bridge wire protocol on one side and the OpenAI Realtime API WebSocket on the other: barge-in, function tools, on-demand vision, call governors. PCM 16k on the wire,

LLM-based transcript enhancement for cuttledoc

Custom n8n node for high-performance MongoDB Vector Search, standard queries, and custom JSON aggregations.

Bootstrap package for @opencode-ai/ai

n8n custom nodes for n8n to interact with Feishu/Lark, including Lark Bot, Lark MCP, and Lark Trigger.

Ternary Additive Contrastive LLM — CPU-friendly integer neural network

Varasto HTTP client that connects to remote storage

n8n node for the Lohnica German payroll API: gross-to-net, net-to-gross and cost-to-net calculations plus health insurance lookup

Grain's storage-agnostic workflow engine — a pure advance() reducer and a RunStore port.

Client-side Frugal-AI layer: context apoptosis that auditably cuts LLM inference cost per deployment.

Parses and packages AIND VR Foraging behavioral sessions into tabular (parquet) and NWB outputs.