Blog

The announcement fits in one line: Memori is a member of the NVIDIA Partner Network (NPN). What sits behind it is longer, and worth telling in full: a ladder of deployments already tested and published, optimized models served inside the customer's perimeter, and a governance infrastructure that stays the same whatever the engine. Partner program memberships are usually announced with a logo on a website, and that is where they end. We prefer to tell this one backwards: the work first, the badg

The Suite is now up to seven connectors that talk to each other, inside a catalog of thirty six. But the list doesn't say anything. What says something is the day to day: here are four real people, with made-up names and real problems, and what changes when an agent enters their Monday. There's a wrong way to tell the story of a platform, and it's listing its parts. Seven connectors in the Suite, twenty-nine toward the systems of the world, databases, mail, calendars, payments. All true, and al

In every company, operational knowledge lives in three places: in someone's head, in a PDF nobody opens, and in the memory of whoever was there last time. The meeting minutes get written "the way Franca does it," a complaint gets handled "the way the guy who's now retired used to say," the monthly report has a format that exists only because someone remembers it. Then Franca goes on vacation, and it turns out the procedure was never written down anywhere. AIsuru Skills exists for exactly this:

There's a part of our work we talk about far too little. We often tell the story of individual connectors, one at a time, as they're born. But the real value isn't in the single piece: it's in the whole catalog, and in what happens when the pieces work together. This morning at 6am, for instance, an agent crossed five company systems without waking anyone up: the scheduler opened its session, it read a shared mailbox, retrieved a price list from SharePoint, calculated variances on real data, up

The best open weight models have nearly closed the gap with the closed giants. This changes everything for anyone who wants artificial intelligence that thinks inside their own perimeter: healthcare, finance, public administration, manufacturing, anyone with data that cannot leave. But the narrative talks about benchmarks and stays silent on two things: what it really costs, step by step, and what it takes for an in-house model to be sovereignty rather than a private wild west. This guide tells

A conversational agent, on its own, knows how to talk. With the AIsuru Suite it learns to remember, act on its own, calculate precisely, consult other agents, be used as a service, and build its own application through conversation. This article covers all six original connectors in the Suite, with real cases already running in production and scenarios where you could use them tomorrow morning. Let's start with the scenes In one company there's an agent that keeps ISO document review under c

Today we're introducing AIsuru Vibe Coder, the connector (patent pending) with which an AIsuru agent builds its own application by talking with its owner: databases, interfaces, forms, automations and access rules, in the same conversation where they are requested. In this article we tell you everything: what it does, how it does it step by step, why it never invents a piece of data, how it orchestrates the other connectors in the Suite and the catalog, what testers and customers have already b

An agent answers. A team of agents works. Between these two sentences lies the most important shift enterprise AI is making these days: from chatbot to process. They're called multi-agent architectures: systems in which several specialized agents coordinate to complete a task, each with its own role, its own knowledge and its own rules. This isn't a lab topic. According to Gartner, enterprise inquiries about multi-agent systems grew by 1,445% in just over a year, and Gartner itself warns that m

AI agents don't enter a company in place of people: they enter in place of one specific part of the work, the part no one will miss. And in doing so they change processes, which is the thing that really matters. In this article we line up what the data says, what we see in projects, and the method we follow when we enter a company, between training and platform. 2026 is the year of selection, not adoption Adoption has already happened. According to "The State of AI" (McKinsey), 88% of organi

Updated as of July 2026. Comparison based on public documentation of both platforms. Let us know about any inaccuracies: we'll fix them. If your company uses Microsoft 365, the question is inevitable: why not build AI agents with Copilot Studio, since it's already there? It's a fair question, and it deserves an honest answer: for some use cases Copilot Studio is the natural choice. For others it becomes a fence. This page helps you understand which side you're on. The difference in one senten

"The mistake many people make is aiming for the latest language model, when instead you need to immerse it in an infrastructure". This is the conviction of Nunzio Fiore, CEO and founder of Memori, an Italian company founded in 2017 with the goal of letting anyone create AI agents back when they weren't even called that yet. The result is a proprietary platform, AIsuru, that allows businesses and professionals to build conversational agents without writing code, connecting them to business proces

There are concepts we explain every week, in demos, meetings, and workshops. At some point we tried to condense them into a single illustration: on one side, the chaos companies experience when they adopt AI agents without foundations; on the other, the infrastructure that makes those same agents secure, useful, and governed. In between, a path. This article is a guided tour of that image. We describe it meticulously, detail by detail, because every element of the drawing corresponds to a real

This week Memori completed the picture: with the arrival of ISO 9001:2015 (Quality) and ISO/IEC 27001:2022 (Information Security), the company now holds all six of the attestations it had set out to obtain. Together with the already-obtained ISO/IEC 27017:2021, ISO/IEC 27018:2020, ISO 42001:2023, and compliance with the NIS2 directive, this closes a long path made of documentation, evidence, and cross-departmental work. But a list of acronyms, on its own, doesn't say much. The question that mat

An AI agent is only as good as the systems it can access. An assistant that "knows everything" in the abstract is of little use, an assistant that can read policies on SharePoint, open a ticket in Dynamics 365, query the ERP, or check courses on the LMS suddenly becomes useful. In a company, the bottleneck is almost never the model: it's the secure connection to real data and real systems. And this is where a problem arises that blocks large scale adoption. To connect those systems, someone has

During almost every demo, we show an agent reading Outlook, navigating SharePoint, pulling data from Dynamics, updating SQL Server, and generating a branded Excel report. People are impressed. And then comes the same question, every time: "Great. But what about our API? The internal management system, the order portal, that custom service we built three years ago?" Until yesterday the answer was "we're working on it" a dedicated connector was required. Starting today, the answer is simply "yes!

A conversational agent that responds is useful. An agent that acts — sends emails, writes to a database, schedules jobs, queries other agents — is a different category of product. But the moment an AI can take real actions on real systems, the question is no longer «does it work?». The question is: who is acting, with which credentials, and who allows it? This is the question that gave rise to AIsuru's MCP Gateway: the control plane that sits between AIsuru agents and the outside world, and tha

On the night of June 12th, Italian time, the US government suspended Fable 5, the most powerful publicly available artificial intelligence model, for all non-US citizens. Not due to a malfunction. Due to a decree. Imagine a European company that had built a critical process on top of it. It would have found itself without a model, without notice, because of a decision made in a room where it had no seat. When I shared an initial reflection on this topic, a friend wrote me something that struck

An AI agent is only as useful as the systems it can access. That's why at AIsuru we've built (and keep growing) a collection of over 20 MCP (Model Context Protocol) connectors, orchestrated by a proprietary gateway that handles security, identity, and permissions. What you see in the image is the library that every AIsuru agent can use today, without writing a single line of code. What this means in practice Microsoft 365 productivity The agent reads and sends Outlook emails, even with atta

89 operations across 18 Cloudflare services, accessible through a conversational agent. No dashboard, no CLI: just a conversation. The problem Managing a modern cloud infrastructure means constantly moving between dashboards, terminals and documentation. Creating a Worker, connecting it to a database, configuring storage and cron jobs means going through dozens of different screens, each with its own interface. We wanted to try a different approach: what happens if an AI agent can do all of

Imagine telling an AI agent: "manage a client directory for me with name, company, industry, last contact date, and notes." No spreadsheet to set up, no database to configure, no application to develop. The agent understands the data structure you need, creates it on its own in its database, and from that moment manages it: inserting, searching, updating, deleting. You keep talking in natural language. It works with the data. This is MCP Persistence, the new feature available on AIsuru. A dat

Today we're releasing mcp-sharepoint as open source — an MCP (Model Context Protocol) server that lets any AI Agent interact directly with Microsoft SharePoint through the Microsoft Graph API. The repository is available on GitHub: github.com/memori-ai/mcp-sharepoint The problem it solves SharePoint is the document backbone of millions of companies. Procedures, manuals, contracts, technical documentation, templates: it all lives there. But when a team works with AI agents — on Claude, on AIs

PREMISE The adoption of artificial intelligence in a company represents a strategic opportunity, but it requires a structured approach to ensure security, regulatory compliance, and maximization of benefits. This document provides practical guidelines for building an effective corporate policy on AI governance. 1. WHY A CORPORATE AI POLICY IS NEEDED The Problem: Shadow AI The "Shadow AI" phenomenon occurs when employees use unauthorized artificial intelligence tools (such as public ChatGPT

On January 27, 2026 in Bologna, there is an unmissable event for anyone who wants to bring artificial intelligence into their company the right way. AI adoption in businesses is no longer a matter of "whether", but of "how". How can you integrate AI Agents while complying with regulations? How can you avoid Shadow AI and ensure effective governance? How can you move from experimentation to production? On January 27, 2026, at the Auditorium Biagi of Confindustria Emilia Centro in Bologna, we wi

What is an AI agent (and why it’s not just a chatbot) An AI agent is a system that understands natural-language requests, decides on a plan of action, and interacts with external tools to achieve a goal. It doesn’t just “tell you what to do”: it does it. Examples: open a ticket, update an order, write an email, extract a record from CRM/ERP, fill out a form, retrieve a document. * Classic chatbot: static Q&A, few integrations, no deep memory; * AI agent: function calling, memory, policies an

1. How it all began When, at the end of 2024, Memori and Araneum helped Lenovo assemble its first server dedicated to LLMs, the idea was straightforward: see whether an open-source model could withstand a real company’s workload without relying on the cloud. That pilot, described in our first report, drew plenty of attention. Six months later we went back to the lab—this time with a more powerful machine, more mature models and a more ambitious goal: bringing enterprise-grade conversational A

In the rapidly evolving landscape of conversational AI, several platforms stand out for creating custom AI agents and chatbots. This report provides a detailed comparison of four notable solutions: AIsuru by Memori AI, Microsoft Copilot Studio, Amazon Bedrock Agent Maker, and OpenAI’s GPTs (custom ChatGPT agents). We examine their features, ease of use, cost, customization options, integration capabilities, AI models used, and security/privacy considerations. The analysis highlights the strength

But what is AIsuru? An LLM? A chatbot? An orchestrator? And what are its sales channels? And what is the AI Academy? These are some of the questions we received at our stand at the AI FESTIVAL 2025. So here we have answered and clarified in the most concise and simple way possible. Which LLM is the platform based on? AIsuru is not a Large Language Model (LLM) itself, but a platform that can integrate different existing LLMs. The platform: * Uses proprietary natural language processing (NLP

Conversational artificial intelligence is revolutionizing how companies interact with customers and employees. According to Bain & Company's "Global Technology Report 2024," in Italy, 7% of small and medium enterprises (SMEs) and 24% of large companies have already implemented artificial intelligence-based solutions. But there's a big difference between a simple chatbot and a truly effective AI Agent. The key? The ability to perform concrete actions beyond simple dialogue. This is where AIsur

Imagine having to search for specific information in over 130 pages of technical documentation. How long would it take you? What if you could simply ask a question and get an immediate answer?  At Memori, we tackled this challenge by developing Manuela 2.0, a revolutionary system that transforms static documentation into an intelligent virtual assistant. Thanks to its integration with AIsuru, Manuela 2.0 doesn't just search for information: it understands users' questions and provides precise,

We're proud to announce that the Memori team, composed of Daniel Pezzettone and Michele Parigi, has secured first place in the "AI Business Challenge" category at the International AI Hackathon 2024. The competition, sponsored by tech giants including AWS and Anthropic, brought together teams from around the world to develop innovative artificial intelligence-based solutions. AIsuru’s power in action The Memori team's success was made possible through the strategic use of AIsuru, our conversa

TL;DR: How an LLM can say everything and its opposite, and therefore needs to be governed and guided. Who am I: My name is Nunzio Fiore, and I am the CEO of Memori.ai, a company specializing in conversational artificial intelligence. We have developed a SaaS and PaaS platform that allows consumers and businesses to customize and control the responses of a conversational AI. We use LLMs to generate text but implement various strategies to control the content. During events and presentations, I

AISURU: the innovative platform that allows you to share knowledge through artificial intelligence. Companies and creators can leverage AISURU to create and manage their own AI team, integrating it into various business processes such as training, marketing and other operational areas, making these artificial intelligences active and effective members of the work team. Among the many features of AISURU, 'Deep Thinking' stands out, which provides AI with persistent memory, allowing them to

We believe that LLMs can also be exploited to verify if your online presence accurately communicates the concepts that are most important to you. Whether it's through articles about your work, your website, social media, or blog, you want to ensure you've conveyed your key concepts effectively. Sometimes, you might assume something is understood when it's not well communicated. Therefore, a simple interaction with an LLM can be a new way to check your indexing and communication skills. Here's a

We can highlight several strengths of AIsuru compared to other products in the field of conversational artificial intelligence: 1. Content Customization and Control: AIsuru allows for detailed customization of content, offering users the ability to define who can receive responses, in which context, and in what language. This includes the ability to create various types of interfaces for sharing AI across different platforms, such as totems, the web, and virtual reality . 2. Integration with

It is an exciting time for us here at Memori.ai, as we have been working hard to improve TwinCreator, and we are happy to announce some amazing new features for the React and Webcomponent libraries in our product.

In an increasingly digitized world, artificial intelligence is radically transforming various fields, and human resources is no exception. Among the various applications of AI, conversational AI is proving to be particularly revolutionary.

In this article we discuss how conversational AI, especially when made more accessible through solutions like TwinCreator, can offer tremendous opportunities in the IoT field.

From the past of pre-programmed chatbots to the era of generative AI and TwinCreator, we discuss current trends, future possibilities, and the importance of ethical and responsible use of these powerful technologies.

🌐👥 We have always believed in the power of ethical Artificial Intelligence and have committed ourselves to developing our solutions in full compliance with the European Community's AI guidelines. 🔒🇪🇺

In this article, we will analyze the features of TwinCreator and the benefits this platform can offer to companies.

We have recently changed the Dynamic Intents API caching policy. Additionally, we are going to release soon important changes to the Open Session API that will add the user's birth date as a mandatory parameter.

It is now possible to create a VR demo in just a few clicks!

Thanks to our new 'smart file import' feature, creating sophisticated AIs is now easier than ever with TwinCreator.

Are you ready to take your online shopping experience to a whole new level? With TwinCreator, the state-of-the-art conversational agent creation solution, you can do it.

Our product strategist was playing around with one of our twins and decided to record a ‘smooth as butter’ 🧈conversation as a demo of the current power of TwinCreator.

With the new ChatGPT integration, generating responses for unknown questions is faster and easier than ever before. TwinCreator's "human-first" approach to generative AI ensures that humans are always in control.

Artificial intelligence (AI) has revolutionized the way we interact with technology, and one of its most exciting developments is the chatbot.

Interoperability will be applied way beyond games, digital apparel, and a few other types of assets. It will become the foundation on top of which rich experiences across all fields will be created and shared.

Now the AI's built with Memori support a code-snippets as content type.

To all our technical followers and developers out there, we have exciting news for you! Working with the Memori API and creating sophisticated digital twins is now easier than ever, cause we just released our API client!

A glimpse into our vision for the future of digital twins.

We are officially landing in Decentraland! Now you can add your unique AI's to the Metaverse.

We are proud to be part of Cubbit's Next Generation Cloud Pioneers network, to lead AI towards more responsible practices

We're proud to partner with Ready Player Me. Now our users can create custom avatars for their AI's built with MemoryTwin and TwinCreator.

A collection of statistics and predictions on the future of eCommerce and the role of conversational AIs