Search

stream-first Agent Runtime.

n8n community node for AI video generation with MoE, attention residuals, and 8x upscaling

n8n community node for BTCMatic — Bitcoin event engine: react to rule fires, manage rules, run backtests and send events into webhook-triggered rules

Send and receive SMS through your own phone with SimGate

Logali HANA Guard: security-first SAP HANA community node for self-hosted n8n

Route each Pi session's first task to an appropriate model

AI-powered code review with secret detection, approval workflows, and multi-LLM support

Lint LLM chat-completion prompts for cross-provider portability issues

Automatic RAG Pattern Optimization Engine

Capture the literal HTTP request/response of every LLM provider call (by patching globalThis.fetch) and show them in a Wire Trace session tab

DSH LLM API pool manager: multi-subscription opencode go management with official usage/balance (pure API key), usage-based hot-switch routing, and a settings-page UI. 多 LLM API 订阅池管理:官方余额/用量查询 + 用量感知热切换 + 设置页图形化管理。

OGPT - AI coding assistant for the terminal with a built-in local engine

XMode — универсальный клиент для всех моделей Tokenly (Anthropic, OpenAI, Google)

LLM Wiki panel: right-column file tree, knowledge graph, markdown/PDF reader, and upload flow for the DeepSeek Harness wiki

LLM Wiki host engine: RPC for the wiki panel, ingest/search/graph/lint, the wiki_query tool, and a prompt section (Karpathy Wiki methodology)

Atlas RAGKit — Local-First RAG Engineering Platform

Declarative runtime-state management for a LiteLLM proxy: reconcile users/teams/keys/credentials/models from a YAML spec.

OpenCode provider plugin for Sockless LLM Router — point it at the router's API endpoint and every model is discovered automatically, with context size, tool-calling, vision and reasoning support carried over.

Vercel AI SDK inference and loop adapters for @aevr/agents.

n8n node that extracts structured data from conversations using Qwen and a strict JSON Schema