Search

Visual Retrieval-Augmented Generation — render, embed, index, search, train

text style extension for tiptap

n8n ChatModel node with extended reasoning/thinking support for OpenRouter, DeepSeek, and any OpenAI-compatible API

Least Cost Routing for LLMs — route every model call to the cheapest available provider, fall back automatically, and track real cost. Built for the Vercel AI SDK.

Nwire — S3 storage adapter. Works with AWS S3, MinIO, Cloudflare R2, Backblaze B2, and anything else speaking the S3 API. Wraps @aws-sdk/client-s3 + @aws-sdk/s3-request-presigner.

The simplest Python client for free access to top-tier AI models (GPT-4.1 Nano, DeepSeek, Gemini Flash, Claude Haiku)

An Entari Plugin for LLM Chat with Function Call

Lightweight evaluation framework that unifies inference through a single VLLM sampler and runs IF-EVAL, IFBench, WritingBench, HealthBench, Arena-Hard, and AlpacaEval end-to-end.

Dead-simple Groq LLM chaining. No bloat.

Route prompts to the right LLM automatically. Supports Groq, OpenAI, Anthropic.

Pi extension package for Claude-compatible header and request-path adaptation across multiple providers.

Um cliente, todos os LLMs. Roteamento por intencao, fallback automatico e tracking de custo.

Sycamore is an LLM-powered semantic data preparation system for building search applications.

TraceLLM — Open-source LLM observability, tracing, and replay infrastructure.

OpenClaw integration package for Radware Agentic AI Protection

Add your description here

Pi agent extension for Claude models via Google Cloud Vertex AI

LangChain adapter for emitting AeroGraph traces from agent workflows.

llms.txt / llms-full.txt / per-route Markdown generators.

n8n community node for Provedit. Record AI tool invocations to a tamper-evident chain, check policy decisions, and gate workflows on allow/require_approval/deny.