... Today we re open-sourcing the core memory engine behind @MnexiumAI : CORE-MNX. GItHub NPM For us, this is a product decision and a philosophy decision. Memory infrastructure is becoming foundational for serious

... Managing conversation state Securing API keys ... and it still wont remember anything about your users That s a lot of engineering just to let users ask questions. Demo Visit mnexium.com or mnexium.com/docs and try it out on the @MnexiumAI website. The Solution NPM Package - https://www.npmjs.com/package/@m... npm install @mnexium/chat One package. Three ways to use it: React / Next.js import { MnexiumChat } from '@mnexium/chat'; export default function App() { return ( <> <YourApp /> <MnexiumChat endpoint="/api/mnx ... ... What You Get Floating widget with modern glass design Real-time streaming responses Markdown rendering Dark/light themes + custom colors + logo Multi-provider support (OpenAI, Anthropic, Gemini) Persistent memory across sessions Why

... built @MnexiumAI and I thought the fastest way to get folks to try was it to build a chat plug-in for websites. I am providing free keys (however much usage it may be) to anyone who is willing to try it. The plug-in can be found on NPM https://www.npmjs.com/package/@m... npm install @mnexium/chat <MnexiumChat endpoint="/api/mnx" /> Out of the box you get: A professional chat UI at the bottom left or right of your ...

... experience AI with persistent memory no signup required. mnexium.com/chat What You'll See The demo is a real-time chat interface that shows exactly how Mnexium

... When people talk about AI memory, it s usually framed from the developer s side. How do we store it? How do we retrieve it? How do we keep context alive? This is where @Mnexium

... just shipped multi-provider support in @MnexiumAI so you can change LLMs without resetting conversations, user context or memories. The problem When teams switch providers, they usually lose everything: conversation history user preferences long-term memory learned context Every conversation starts from zero. Not great for UX or retention. What

... Most AI products eventually hit the same problem They forget who the user is and the experience feels generic again. We ve been working on @Mnexium

... When building AI agents with long-term memory, debugging is a challenge. You know something was remembered but: When was it created? What replaced it? Why is it being recalled now? Why was it created as a memory in the first place? Memory Graphs is our first attempt to fix that. See memory evolution Watch facts evolve across conversations: favorite color = blue green red yellow Trace exact origins Every memory links back to the message that created it. Visualize recall ... ... hover understand the full memory timeline instantly. Why this matters Debug memory bugs faster Build user trust with transparency Spot conflicts and bad supersession logic Maintain a full audit trail for compliance We re really trying to build @Mnexium

... profile schemas and keeping them in sync Managing long chat history + summarization pipelines Juggling different formats across OpenAI, Claude, etc. Hosting, scaling, backups, monitoring Timeline: 2 4 weeks (plus ongoing maintenance) Cost: engineering time + infra + vector DB fees With @MnexiumAI , memory is built-in const client = new OpenAI({ baseURL: " https://mnexium.com/api/v1 ", defaultHeaders: { "x-openai-key": OPENAI_KEY } }); await client.chat.completions.create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello" }], mnx: { subject_id: "user_123", history: true, // Chat history learn: true ... ... replacement for the OpenAI SDK When should you use

... MnexiumAI Now supports all three major