Graph/RAG & NeSy AI : du doc brut au raisonnement
Du document brut au raisonnement : extraction d'entités, construction de knowledge graphs (RDF vs Neo4j) et IA neuro-symbolique — combiner la flexibilité des LLMs et la rigueur de l'IA symbolique.
Daily discussions
Official announcements
Announcements & events
Announcements & chat between members
Source code & open-source projects
Du document brut au raisonnement : extraction d'entités, construction de knowledge graphs (RDF vs Neo4j) et IA neuro-symbolique — combiner la flexibilité des LLMs et la rigueur de l'IA symbolique.
A short email before each meetup. Nothing else.
Engineer, researcher or student — a talk, a live coding session, a real-world experience report, a paper reading. We love first-timers.
Quick reply. Free format, free length.
The community
Our sessions span the full spectrum — from machine learning to autonomous agents, from computer vision to symbolic reasoning, from GenAI to ethics. We welcome all speakers: engineers, researchers, students, curious minds.Beginners and experts alike.
Engineers, researchers, students share what they're building.
We read and dissect together the papers that matter.
Building an agent, an LLM, a pipeline — live, together.
What works, what breaks, what we'd do differently.
Conversations after every talk. No question is too beginner.
ML, DL, GenAI, agents, NLP, vision, XAI, ethics, symbolic reasoning.
Past sessions
A look at the latest sessions. Every month, a new topic — AI agents, MCP, GPT from scratch, sandboxing, RAG, recent papers…
Mathieu Cordebard — web developer & WebRTC architect
A subjective, non-specialist take on how AIs work and what they change: how these models learn, what they cost (data, energy), and how they reshape the way we create, work, and think.
Léandre Le Bizec — Solutions Engineer at Dust
Online session (English). How teams ship AI agents day-to-day across support, ops, finance, and engineering. Live demo: building an agent from scratch, plugged into existing tools and data, followed by Q&A.
Teodora Djikic-Stojsic, Emil Sayilov & Anjila Ben Frej — Research Engineers, iCube
English session. Intro to medicinal chemistry and drug discovery, then a chemistry-specialised LLM: structured reasoning, analogue-series datasets, and an agentic layer with tool-calling to assist molecule research.
Sonny Mupfuni — AI engineer & PyTorch ambassador
Building AI agents with the Google Agent Development Kit. Survey of use cases: customer service, finance, supply chain, software development, cybersecurity.
Raphael Antoine — healthcare interoperability expert
Real-world reflections after a year of daily AI agent use. Concrete takeaways, no dogma: where trust is earned, where supervision stays essential.
A hands-on look at the Model Context Protocol (MCP) and how it connects AI agents to real data, services, and applications. How an agent talks to an MCP server to perform concrete actions.
Your AI agent runs code, spawns shells, hits the network. How do you isolate what it shouldn't do? A tour of isolation boundaries: Docker, gVisor, Firecracker MicroVMs.
Follow-up to the agents session (Jeremy Howard / Claudette). This time we apply the concepts with the Google Gemini SDK: 30 min intro to AI agents, then live coding.
English-speaking session. We follow the “How to Solve It with Code” course by Jeremy Howard and Johno Whitaker, reproducing the code live to understand how an AI agent works.
We follow Sebastian Raschka's “Build an LLM from Scratch” series. Bring your laptop: we build a large language model step by step, together.
Continuation of the interactive session following Andrej Karpathy's video. We pick up where we left off and keep building GPT.
Interactive session following Andrej Karpathy's iconic video: we build GPT from scratch, in Python, together.
Bogdan Penkovsky (Alysophil) — plus AlphaFold2 talk
Double session: Quantum Machine Learning, myths and realities (by Alysophil R&D), followed by a presentation on protein structure prediction with AlphaFold2.
Frequently asked questions
A non-profit community running monthly AI meetups in Strasbourg: talks, paper readings, live coding and field reports on machine learning, deep learning, generative AI and autonomous agents.
No. Meetups are open to everyone — engineers, researchers, students or the simply curious. Beginners and experts are equally welcome.
Yes, all meetups are free. Registration (via Meetup) is only requested for venue access.
About twice a month in Strasbourg — often at the Digital Village. Some sessions are also available online.
French and English, depending on the speakers. Each session's language is shown on the event.
Engineers, researchers and students can present a talk, a live coding session or a field report. Contact us from the site or the Meetup page — first-timers are encouraged.