Open source, in Python, compatibile con vari LLM ed estendibile tramite plugin: queste sono solo alcune delle potenzialità del framework Cheshire Cat AI!
Report
Share
Report
Share
1 of 20
Download to read offline
More Related Content
Similar to Crea il tuo assistente AI con lo Stregatto (open source python framework)
Accessibility At Scale - Tiffany Tse - ShopifyTiffany Tse
This document discusses building accessible and inclusive design systems. It provides examples of implementing accessibility best practices like WCAG and ARIA guidelines. It also emphasizes the importance of maintaining design systems, documenting components, and creating a culture of contribution to support accessibility.
Discover the technology behind "The Heretic" – Unite Copenhagen 2019Unity Technologies
Unity's award-winning Demo team, creators of Adam and Book of the Dead, showcases how Unity can power high-end visuals for game productions. These slides show how the team used the latest features in the High Definition Render Pipeline such as Post Processing, Shader Graph, Visual Effect Graph, and Timeline to create their latest amazing real-time short film, The Heretic.
Speaker: Mark Schoennagel – Unity
Watch the session on YouTube: https://youtu.be/CCnhPyK1v9E
Simple Ways to Get Your Organization to Adopt the AsyncAPI SpecAxway
Speaker: Emmelyn Wang, API Strategist, Office of the CTIO
Conference Title: First-Ever AsyncAPI Global Online Conference
AsyncAPI community has great culture. Here are 3 ways to influence, equip, and empower your company, product leader or engineering organization to adopt the AsyncAPI spec.
#asyncapiconf
1) The document discusses plans for developing an autonomous robot called RamuDroid to help clean roads and outdoors.
2) Key components of RamuDroid discussed include a Raspberry Pi, Arduino, camera module, ultrasonic sensor, GPS, temperature sensor, relays, and rotating brushes.
3) The document outlines a proposed 6 month timeline for developing a prototype, which includes defining the technical architecture, adding communication modules and sensors, and exploring power conversion and autonomous driving capabilities.
This session covers why you should pay attention to the accessibility of your web site or application and then walks you through how to do it using WAI-ARIA and JavaScript.
The document discusses getting started with Azure AI tools and services. It provides an overview of Azure AI platforms including tools for knowledge mining, machine learning, and AI apps and agents. It then discusses how to use these tools through demos of the Azure Bot Service, LINE chat integration, Computer Vision API, and Cognitive Services APIs. Tutorial links are also provided.
This document describes EMOTBOT, a chatbot that recommends movies and songs based on user preferences. It was built using Python and integrates with an HTML/CSS frontend using the Flask framework. The chatbot uses NLP and APIs to carry out a conversation to determine a user's preferred genre and then suggests movies. It also includes a music player webpage to listen to songs. Future enhancements could include accessibility features for visual impairments, automatic ticket generation, sentiment analysis, and playlist customization.
API Management: Rise of the Planet of the Apps (2016 09-26 - Porto.Data)Sandro Pereira
Azure API Management que permite proteger, publicar e analisar as nossas APIs e microsserviços numa gateway de API’s escalável.
O objetivo desta sessão é partilhar experiência sobre as capacidades do Azure API Management: como podemos começar a usar; como podemos modernizar as nossos web services, adicionar novos protocolos de segurança; como podemos criar um site de documentação e testes para os developers; como pode ser a base para os seus projetos híbridos de Integração; e explorar algumas das suas funcionalidades principais.
E como sempre, não é esperado que todos tenham conhecimento aprofundado desta tecnologia, mas apesar disso espera-se que esta será uma sessão interativa por forma a tentar ajudar-vos a compreende-la melhor.
1) Altanai Bisht and Deepak Aagri present RamuDroid, a robot designed to clean Indian roads using IoT, WebRTC, and live streaming capabilities.
2) The document outlines the stages of developing RamuDroid, including setting up an electronics lab, adding communication via GSM, building the robot's basic structure, enabling remote streaming and navigation with a Raspberry Pi camera and WebRTC, and creating a web interface.
3) The project aims to create an autonomous robot that can analyze camera frames and automatically make real-time decisions to sort waste into recyclable and non-recyclable categories.
Progressive Enhancement with ARIA [Carsonified HTML & CSS Online Conference]Aaron Gustafson
Designing and developing with accessibility in mind has numerous benefits: it makes your website usable by everyone, it makes your content inherently more search engine friendly, and it makes providing context-sensitive interfaces (e.g. mobile) even easier. In this session, Aaron Gustafson will provide you with a quick refresher on progressive enhancement and show you where the Web Accessibility Initiative's Accessible Rich Internet Applications (WAI-ARIA) spec fits into it all. Throughout the talk, Aaron will provide numerous examples of how to weave ARIA into your projects and how to use ARIA, in concert with JavaScript, to dramatically enhance the usability of client-side widgets.
ABD322_Implementing a Flight Simulator Interface Using AI, Virtual Reality, a...Amazon Web Services
This workshop explores the technology options, architectures, and implementations associated with instrumenting AR, VR, and simulated worlds. Using flight simulation as the primary use case, you learn to consume, process, store, and analyze high velocity telemetry as well as exploring control plane implementations using AWS IoT, AWS Lambda, Amazon Kinesis, and Amazon SNS. This is a hands-on workshop and you need a laptop (tablets are not suitable). You should have a solid understanding of AWS products and Node.js.
Crab - A Python Framework for Building Recommendation SystemsMarcel Caraciolo
Crab is a Python framework for building recommendation engines. It began as a Mahout alternative for Python developers and is being rewritten as a Scikit-learn submodule. Crab currently features collaborative filtering algorithms and evaluation metrics. Developers are working in sprints to optimize performance by integrating Numpy and migrating Crab to work as a Scikit in order to make it faster and more accessible to the scientific community.
The document discusses various aspects of Web 2.0 including its definition, popular applications, technologies like Ajax and APIs, design aesthetics, and the importance of user participation and community. It provides examples of microformats, buzzwords, and pillars of Web 2.0. Additionally, it offers tips for building your own Web 2.0 application and humorously discusses Web 2.0 cargo cultism.
The Browser, the User and the Library (How to to be in between)Guus van den Brekel
Tutorial delivered in the NIFT Institute, New Delhi, India as part of the ICLAM2011 Conference, http://www.nift.ac.in/ICLAM_2011/index.htm
This practical workshop will demonstrate the use of Web 2.0 technology to empower users and librarians.
During a hands-on session, participants will work with these tools.
You will develop a library Toolbar, tailor-made services via personal start page software like Netvibes, making use of RSS-feeds, Widgets and Browser extensions
WebRTC and the Web Audio API allow real-time communication and audio/video processing capabilities directly in the browser. WebRTC provides APIs for capturing media streams from devices and establishing peer-to-peer connections, while dealing with challenges like firewalls and NAT using ICE, STUN and TURN. The Web Audio API enables efficient audio stream manipulation through a processing block model. While building full-featured video chat applications with WebRTC alone can be difficult, these capabilities open opportunities for applications involving real-time media and audio processing directly in the browser.
Oltre l'hype: vulnerabilità e limiti dell'intelligenza artificiale.pdfCommit University
Non è tutto oro quello che luccica, in questa presentazione esploreremo le principali criticità e i rischi associati all'intelligenza artificiale (IA). Come si può attaccare un sistema informatico allo stesso modo esistono gli attacchi ai modelli di machine learning, come l'avvelenamento dei dati e gli esempi avversariali, che minano l'integrità dei sistemi. Inoltre, si evidenzia come i bias nei dati di addestramento possano portare a decisioni discriminatorie, influenzando settori cruciali come la giustizia e l'occupazione. La necessità di una spiegabilità nell'IA viene sottolineata per garantire trasparenza, fiducia e un uso etico della tecnologia. L'obiettivo è fornire una visione equilibrata, sottolineando l'importanza di una vigilanza continua e di miglioramenti costanti per sfruttare il potenziale dell'IA in modo responsabile.
Come funzionano i Retrieval-Augmented Generators (RAG) e quanto i database vettoriali sono fondamentali per poter memorizzare e utilizzare le sorgenti dati aziendali e personali?
Breaking REST Chains_ A Fastify & Mercurius Pathway to GraphQL Glory.pdfCommit University
This document contains slides from a presentation by Luca Del Puppo about building GraphQL servers using Fastify and Mercurius. The presentation introduces GraphQL and its advantages over REST APIs. It then discusses why Mercurius is a good choice for building GraphQL servers on Fastify and outlines some features it provides out of the box. The presentation concludes by providing resources for learning more about Fastify, Mercurius and building GraphQL servers.
Collaborazione, Decisionalità e Gestione della Complessità nel Tempo: cosa ...Commit University
Vuoi migliorare la gestione dei progetti a lungo termine con team multidisciplinari e prendere decisioni rischiose in modo sicuro e ponderato? Non perderti il nostro workshop gratuito!
Antonio Dell’Ava, Frontend Developer di eDreams Odigeo, condividerà strategie per aiutarti a ottimizzare la collaborazione nel tuo team, scegliere gli strumenti giusti per ogni situazione e garantire l’evoluzione del progetto nel tempo
A volte essere pigri è una qualità, evita (quasi) tutte le richieste di personalizzazioni lasciando "finestre aperte" nei tuoi componenti generici.
Gli slots sono un modo per passare il contenuto a un componente in Vue.js. Permettono di definire una sezione nel template di un componente che può essere sostituita dall'esterno.
È inoltre possibile assegnare un nome o uno "scope" agli slots, garantendo così maggiore controllo e personalizzazione sul contenuto. I "named slots" consentono di definire più slots nello stesso componente, assegnando dei nomi specifici.
Gli "scoped slots" ti consentono di accedere dall'esterno ai dati interni del componente.
Quante volte mi è capitato di migliorare applicazioni lente e difficili da ottimizzare, ma poi ho scoperto Qwik e tutto è cambiato.
Con il suo nuovo modello mentale è in grado di fare la differenza e scalare facilmente qualsiasi applicazione.
Non conosci questo framework? Nessuna paura...andiamo a scoprirlo assieme!
Backstage l'Internal Developer Portal Open Source per una migliore Developer ...Commit University
Backstage is an open source platform for building developer portals that unifies all tooling, services, apps, data, and documentation with a single consistent UI. It allows developers to focus on their work by providing a centralized location to create software, manage what they own, and explore the entire software ecosystem. Backstage has a customizable, extensible plugin architecture built with modern technologies to make it easy to develop for and contribute to developer portals in a cloud-agnostic, vendor-neutral way.
Nella giungla degli ORM node, Prisma sta prendendo sempre più piede. Ha migliorato la Developer Experience, si integra perfettamente con Typescript e funziona dannatamente bene con diversi provider. In questo talk, vedrai come Prisma può migliorare il tuo lavoro quotidiano e come ti permette di avere un maggior controllo della tua code base aiutandoti a prevenire fastidiosi errori nella tua applicazione nodejs.
Decision-making for Software Development Teams - Commit UniversityCommit University
Ti senti bloccato quando si tratta di prendere decisioni critiche su aspetti tecnologici? Vuoi conoscere i processi decisionali collaborativi e come applicarli al tuo team?
Francesco Strazzullo, Chief Operating Officer di Claranet Italia, ti insegnerà gli elementi chiave per prendere decisioni critiche su aspetti tecnologici, gestire i requisiti non funzionali e lavorare con processi decisionali collaborativi.
L’Advisor Leader dell’area Game di NABA, Marco Secchi, ti insegnerà come migliorare la gestione degli oggetti in-game e la loro comunicazione utilizzando Unity Engine e Design Pattern Component.
La prototipazione è un’attività fondamentale per “capire facendo”. Lo scopo della prototipazione non è costruire partendo da un progetto definito ma, piuttosto, acquisire dati preziosi per essere poi più consapevoli di prendere la giusta direzione. Alla base delle attività di prototipazione ci sono spesso strumenti low code e no code. Esistono ormai da diversi anni e ultimamente stanno guadagnando sempre più attenzione nella community per la loro immediatezza e velocità. Abbiamo definito meglio le loro qualità e le opportunità che ci sono nel loro utilizzo.
Durante il talk abbiamo approfondito perché è importante prototipare e come questa attività migliora i nostri progetti. In particolare, abbiamo approfondito l’utilizzo AWS Step Functions Workflow Studio, strumento low code prodotto da AWS. Workflow Studio ci permette di imbastire una state machine basata su step functions con uno strumento visuale drag & drop che semplifica moltissimo il nostro lavoro. Abbiamo analizzato cosa lo contraddistingue da altri strumenti e quali sono i suoi punti di forza. Infine siamo passati alla pratica facendo una piccola esercitazione con AWS Step Functions.
KMM survival guide: how to tackle struggles between Kotlin and SwiftCommit University
Kotlin Multiplatform Mobile (KMM) è un SDK per lo sviluppo di applicazioni Android ed iOS che consente agli sviluppatori di condividere la business logic mantenendo UI/UX native.
Ogni SDK/framework cross/multi platform ha i suoi pro ed i suoi contro, e purtroppo KMM non è l'eccezione che conferma la regola.
Se sei uno sviluppatore Android potresti pensare che tutto funzionerà correttamente, ma purtroppo non sarà così quando dovrai confrontarti con Swift.
Se sei uno sviluppatore iOS saprai che Swift è simile a Kotlin, ma non in tutto, dovrai quindi conoscere alcune sue caratteristiche.
In questo talk vedremo quali sono i problemi che si possono riscontrare nell'interoperabilità tra Kotlin e Swift, i motivi che li causano, e come risolverli.
Stai perdendo la testa cercando di convertire il tuo state manager da Vuex a Pinia?
Ecco una guida step-by-step per affrontare questo task senza difficoltà.
I micro-frontend sono uno degli argomenti più interessanti nel mondo frontend dell'ultimo periodo ma nonostante la loro popolarità, non esistono delle linee guida comuni per svilupparli. micro-lc risponde a questa esigenza e permette di raccogliere in un unico applicativo tanti micro-frontend, orchestrandoli e rendendoli parte della stessa applicazione e non più componenti singoli, scollegati e sconnessi.
Fastify è il web framework del momento e diverse aziende in tutto il mondo lo stanno utilizzando in produzione da anni.
Costruito da zero per essere il più veloce possibile, con un overhead minima e una potente architettura a plugin, Fastify fornisce la migliore esperienza di sviluppo, senza sacrificare prestazioni e sicurezza.
Hire a private investigator to get cell phone recordsHackersList
Learn what private investigators can legally do to obtain cell phone records and track phones, plus ethical considerations and alternatives for addressing privacy concerns.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/07/intels-approach-to-operationalizing-ai-in-the-manufacturing-sector-a-presentation-from-intel/
Tara Thimmanaik, AI Systems and Solutions Architect at Intel, presents the “Intel’s Approach to Operationalizing AI in the Manufacturing Sector,” tutorial at the May 2024 Embedded Vision Summit.
AI at the edge is powering a revolution in industrial IoT, from real-time processing and analytics that drive greater efficiency and learning to predictive maintenance. Intel is focused on developing tools and assets to help domain experts operationalize AI-based solutions in their fields of expertise.
In this talk, Thimmanaik explains how Intel’s software platforms simplify labor-intensive data upload, labeling, training, model optimization and retraining tasks. She shows how domain experts can quickly build vision models for a wide range of processes—detecting defective parts on a production line, reducing downtime on the factory floor, automating inventory management and other digitization and automation projects. And she introduces Intel-provided edge computing assets that empower faster localized insights and decisions, improving labor productivity through easy-to-use AI tools that democratize AI.
What's Next Web Development Trends to Watch.pdfSeasiaInfotech2
Explore the latest advancements and upcoming innovations in web development with our guide to the trends shaping the future of digital experiences. Read our article today for more information.
Interaction Latency: Square's User-Centric Mobile Performance MetricScyllaDB
Mobile performance metrics often take inspiration from the backend world and measure resource usage (CPU usage, memory usage, etc) and workload durations (how long a piece of code takes to run).
However, mobile apps are used by humans and the app performance directly impacts their experience, so we should primarily track user-centric mobile performance metrics. Following the lead of tech giants, the mobile industry at large is now adopting the tracking of app launch time and smoothness (jank during motion).
At Square, our customers spend most of their time in the app long after it's launched, and they don't scroll much, so app launch time and smoothness aren't critical metrics. What should we track instead?
This talk will introduce you to Interaction Latency, a user-centric mobile performance metric inspired from the Web Vital metric Interaction to Next Paint"" (web.dev/inp). We'll go over why apps need to track this, how to properly implement its tracking (it's tricky!), how to aggregate this metric and what thresholds you should target.
An invited talk given by Mark Billinghurst on Research Directions for Cross Reality Interfaces. This was given on July 2nd 2024 as part of the 2024 Summer School on Cross Reality in Hagenberg, Austria (July 1st - 7th)
MYIR Product Brochure - A Global Provider of Embedded SOMs & SolutionsLinda Zhang
This brochure gives introduction of MYIR Electronics company and MYIR's products and services.
MYIR Electronics Limited (MYIR for short), established in 2011, is a global provider of embedded System-On-Modules (SOMs) and
comprehensive solutions based on various architectures such as ARM, FPGA, RISC-V, and AI. We cater to customers' needs for large-scale production, offering customized design, industry-specific application solutions, and one-stop OEM services.
MYIR, recognized as a national high-tech enterprise, is also listed among the "Specialized
and Special new" Enterprises in Shenzhen, China. Our core belief is that "Our success stems from our customers' success" and embraces the philosophy
of "Make Your Idea Real, then My Idea Realizing!"
INDIAN AIR FORCE FIGHTER PLANES LIST.pdfjackson110191
These fighter aircraft have uses outside of traditional combat situations. They are essential in defending India's territorial integrity, averting dangers, and delivering aid to those in need during natural calamities. Additionally, the IAF improves its interoperability and fortifies international military alliances by working together and conducting joint exercises with other air forces.
Coordinate Systems in FME 101 - Webinar SlidesSafe Software
If you’ve ever had to analyze a map or GPS data, chances are you’ve encountered and even worked with coordinate systems. As historical data continually updates through GPS, understanding coordinate systems is increasingly crucial. However, not everyone knows why they exist or how to effectively use them for data-driven insights.
During this webinar, you’ll learn exactly what coordinate systems are and how you can use FME to maintain and transform your data’s coordinate systems in an easy-to-digest way, accurately representing the geographical space that it exists within. During this webinar, you will have the chance to:
- Enhance Your Understanding: Gain a clear overview of what coordinate systems are and their value
- Learn Practical Applications: Why we need datams and projections, plus units between coordinate systems
- Maximize with FME: Understand how FME handles coordinate systems, including a brief summary of the 3 main reprojectors
- Custom Coordinate Systems: Learn how to work with FME and coordinate systems beyond what is natively supported
- Look Ahead: Gain insights into where FME is headed with coordinate systems in the future
Don’t miss the opportunity to improve the value you receive from your coordinate system data, ultimately allowing you to streamline your data analysis and maximize your time. See you there!
How RPA Help in the Transportation and Logistics Industry.pptxSynapseIndia
Revolutionize your transportation processes with our cutting-edge RPA software. Automate repetitive tasks, reduce costs, and enhance efficiency in the logistics sector with our advanced solutions.
Fluttercon 2024: Showing that you care about security - OpenSSF Scorecards fo...Chris Swan
Have you noticed the OpenSSF Scorecard badges on the official Dart and Flutter repos? It's Google's way of showing that they care about security. Practices such as pinning dependencies, branch protection, required reviews, continuous integration tests etc. are measured to provide a score and accompanying badge.
You can do the same for your projects, and this presentation will show you how, with an emphasis on the unique challenges that come up when working with Dart and Flutter.
The session will provide a walkthrough of the steps involved in securing a first repository, and then what it takes to repeat that process across an organization with multiple repos. It will also look at the ongoing maintenance involved once scorecards have been implemented, and how aspects of that maintenance can be better automated to minimize toil.
How to Avoid Learning the Linux-Kernel Memory ModelScyllaDB
The Linux-kernel memory model (LKMM) is a powerful tool for developing highly concurrent Linux-kernel code, but it also has a steep learning curve. Wouldn't it be great to get most of LKMM's benefits without the learning curve?
This talk will describe how to do exactly that by using the standard Linux-kernel APIs (locking, reference counting, RCU) along with a simple rules of thumb, thus gaining most of LKMM's power with less learning. And the full LKMM is always there when you need it!
Are you interested in dipping your toes in the cloud native observability waters, but as an engineer you are not sure where to get started with tracing problems through your microservices and application landscapes on Kubernetes? Then this is the session for you, where we take you on your first steps in an active open-source project that offers a buffet of languages, challenges, and opportunities for getting started with telemetry data.
The project is called openTelemetry, but before diving into the specifics, we’ll start with de-mystifying key concepts and terms such as observability, telemetry, instrumentation, cardinality, percentile to lay a foundation. After understanding the nuts and bolts of observability and distributed traces, we’ll explore the openTelemetry community; its Special Interest Groups (SIGs), repositories, and how to become not only an end-user, but possibly a contributor.We will wrap up with an overview of the components in this project, such as the Collector, the OpenTelemetry protocol (OTLP), its APIs, and its SDKs.
Attendees will leave with an understanding of key observability concepts, become grounded in distributed tracing terminology, be aware of the components of openTelemetry, and know how to take their first steps to an open-source contribution!
Key Takeaways: Open source, vendor neutral instrumentation is an exciting new reality as the industry standardizes on openTelemetry for observability. OpenTelemetry is on a mission to enable effective observability by making high-quality, portable telemetry ubiquitous. The world of observability and monitoring today has a steep learning curve and in order to achieve ubiquity, the project would benefit from growing our contributor community.
Video traffic on the Internet is constantly growing; networked multimedia applications consume a predominant share of the available Internet bandwidth. A major technical breakthrough and enabler in multimedia systems research and of industrial networked multimedia services certainly was the HTTP Adaptive Streaming (HAS) technique. This resulted in the standardization of MPEG Dynamic Adaptive Streaming over HTTP (MPEG-DASH) which, together with HTTP Live Streaming (HLS), is widely used for multimedia delivery in today’s networks. Existing challenges in multimedia systems research deal with the trade-off between (i) the ever-increasing content complexity, (ii) various requirements with respect to time (most importantly, latency), and (iii) quality of experience (QoE). Optimizing towards one aspect usually negatively impacts at least one of the other two aspects if not both. This situation sets the stage for our research work in the ATHENA Christian Doppler (CD) Laboratory (Adaptive Streaming over HTTP and Emerging Networked Multimedia Services; https://athena.itec.aau.at/), jointly funded by public sources and industry. In this talk, we will present selected novel approaches and research results of the first year of the ATHENA CD Lab’s operation. We will highlight HAS-related research on (i) multimedia content provisioning (machine learning for video encoding); (ii) multimedia content delivery (support of edge processing and virtualized network functions for video networking); (iii) multimedia content consumption and end-to-end aspects (player-triggered segment retransmissions to improve video playout quality); and (iv) novel QoE investigations (adaptive point cloud streaming). We will also put the work into the context of international multimedia systems research.
What Not to Document and Why_ (North Bay Python 2024)Margaret Fero
We’re hopefully all on board with writing documentation for our projects. However, especially with the rise of supply-chain attacks, there are some aspects of our projects that we really shouldn’t document, and should instead remediate as vulnerabilities. If we do document these aspects of a project, it may help someone compromise the project itself or our users. In this talk, you will learn why some aspects of documentation may help attackers more than users, how to recognize those aspects in your own projects, and what to do when you encounter such an issue.
These are slides as presented at North Bay Python 2024, with one minor modification to add the URL of a tweet screenshotted in the presentation.
Performance Budgets for the Real World by Tammy EvertsScyllaDB
Performance budgets have been around for more than ten years. Over those years, we’ve learned a lot about what works, what doesn’t, and what we need to improve. In this session, Tammy revisits old assumptions about performance budgets and offers some new best practices. Topics include:
• Understanding performance budgets vs. performance goals
• Aligning budgets with user experience
• Pros and cons of Core Web Vitals
• How to stay on top of your budgets to fight regressions
AI_dev Europe 2024 - From OpenAI to Opensource AIRaphaël Semeteys
Navigating Between Commercial Ownership and Collaborative Openness
This presentation explores the evolution of generative AI, highlighting the trajectories of various models such as GPT-4, and examining the dynamics between commercial interests and the ethics of open collaboration. We offer an in-depth analysis of the levels of openness of different language models, assessing various components and aspects, and exploring how the (de)centralization of computing power and technology could shape the future of AI research and development. Additionally, we explore concrete examples like LLaMA and its descendants, as well as other open and collaborative projects, which illustrate the diversity and creativity in the field, while navigating the complex waters of intellectual property and licensing.
11. WHY THE CAT
Cheshire Cat
The AI Assistant Framework
- ready to meow
dockerized
model agnostic
- RAG + action agent
(docs, convos and procedures)
- plugin system and registry
(hooks, tools and forms)
12. THE CAT - AI ASSISTANT FRAMEWORK
Cheshire Cat
The AI Assistant Framework
13. CHESHIRE CAT AI IS LANGUAGE MODEL AGNOSTIC…
Cheshire Cat
The AI Assistant Framework
Ollama
…BUT IT ISN’T A
LLM RUNNER!
20. CHESHIRE CAT AI
Keep in touch!
Cheshire Cat
The AI Assistant Framework
https://cheshirecat.ai
https://github.com/cheshire-cat-ai
https://www.linkedin.com/company/cheshire-cat-ai
https://medium.com/mad-chatter-tea-party
https://discord.gg/cheshire-cat