Search

Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.

Schemas and utilities for the Hexabot agentic workflow DSL.

MongoDB-backed persistent memory provider for the Vercel AI SDK — Session, Semantic, Procedural, Episodic, and Scratchpad memory with Atlas Vector Search.

Easy cross-platform GPU Rendering for Javascript, Python, Swift and Kotlin

n8n nodes for LLM interaction using Vercel AI SDK

Public Sogni Intelligence client — Node.js convenience wrapper for the Sogni SDK plus the public-safe subset of @sogni/creative-agent contracts (ContractRegistry, AssetManifest, RunRecord, tool envelopes). For agent builders, third-party integrations, and

SOTA NPM module for agentic processes using local or cloud LLMs.

Direct @anthropic-ai/sdk adapter for llm-ports. Implements LLMPort with prompt caching, vision, and tool use support for Claude models.

Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision

A CLI to bootstrap an agentic harness for Jahia

QuickJS-backed code mode tool for AI SDK

IBM components (Db2 Vector Store + watsonx.ai LLM and embeddings) as a standalone Langflow Extension Bundle.

Zero-config LLM API inspector — intercepts calls, shows token breakdown and cost estimates in a local dashboard

Hook-first living LLM Wiki runtime for Codex and Claude Code.

LangChain integration for Talor SERP API — 33 search engines in one tool

统一 LLM Provider npm 包：一套统一结构接入 Gemini / Claude / OpenAI Compatible / OpenAI Responses / DeepSeek

SDK for authenticated (non-encrypted) user storage endpoints

Server-side AI crawler tracking for DataFast

n8n community node for Voyage AI Embeddings

Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.