Daytona & Cognee AI Builders - Berlin, November 2026 cover image
Luma·Builder event·IRL

Daytona & Cognee AI Builders - Berlin, November 2026

THU 26 Nov
Thu 26 Nov 2026, 18:00Europe/Berlin
In 4 days Starts in 3d 21h
BerlinBerlin, Germany
TL;DR

Quick take

Daytona & Cognee AI Builders - Berlin, November 2026 is a free IRL builder event at Berlin, Berlin, on Thursday 26 November 2026, 18:00–21:00 CET. It's hosted by Daytona, and registration is on Luma. 146 people are going so far.

The details

About this one

An event dedicated to exploring all things AI Engineering! Event partner: Cognee ​Agenda ​​​​​🕒 6:00 pm – 6:30 pmGathering and Opening Remarks 🎤 Juraj Stefanic, Technical Content Engineer at Daytona ​​​​​​​🕒 6:30 pm – 6:40 pmTalk "Give the Model a Computer: The One Thing Every AI Agent Framework Agrees On"​ 🎤 Mislav Ivanda, DeEx Engineer at Daytona ​​​​​​​​Outline: Building an agent is easy. Deciding where its code runs is the part that follows you to production.…

Read the full details on Luma ↗
The basics

Good to know

When
Thu 26 Nov 2026, 18:00
Where
BerlinBerlin, Germany
Organiser
Daytona ↗
Going / registered
146
Type
Builder event
Format
IRL
Get oriented

Where it’s going down

25 km10 km5 km
1.8 km from Berlin centreOpen in maps ↗
FAQ

Questions people ask

When is Daytona & Cognee AI Builders - Berlin, November 2026?

Thursday 26 November 2026 at 18:00 CET

Where is Daytona & Cognee AI Builders - Berlin, November 2026?

Berlin, Germany

Open in Google Maps ↗
How do I sign up?

Register on Luma.

Is it free?

Free

What else is on in Berlin?

Explore events in Berlin or events in Germany.

Keep the momentum

More in Berlin

See all Berlin events →
MON 23Nov
Mon 23 Nov 2026, 18:00 ESMT Berlin The Venture Club

Have a startup idea and maybe a co-founder? Some legal decisions are much easier to get right at the start than to fix later. The Venture Club is teaming up with V14, a Berlin law firm that advises startups and investors, for a short version of their Legal Starter Pack. It’s built for founders who are still shaping their idea and building their team. Marie Hillebrand and Simonié Schlombs (V14) will cover: IP: how to protect what you’re building, and make sure the company owns it rather than individual founders Co-founder agreements: equity splits, vesting, roles, and what happens if a co-founder leaves Starting to operate in Germany/Europe: the minimum you need to get going legally, from choosing a legal form to what comes before the notary The session ends with an open Q&A, so bring your questions. 📍 ESMT Berlin🗓 Monday 23 November · 18:00–19:00, followed by networking

32 going via Luma
Add to calendar
⋯
MON 23Nov
Mon 23 Nov 2026, 18:00 Merantix AI Campus Merantix AI Campus

Join us for the 12th edition of the Unconference: Engineering AI Together. A no-hierarchy gathering for software engineers, AI/ML practitioners, and technical builders to spend an evening exchanging ideas, pressure-testing approaches, and going deep on the problems they are actually working on. Unlike a traditional conference, there is no preset agenda and no speaker lineup. The sessions are proposed and shaped by the people in the room. Bring a technical question, a problem you are stuck on, something you have learned recently, or simply join a discussion that catches your attention. Previous sessions have explored topics including: AI Coding ToolsCan fully generated codebases deliver secure, scalable architectures, and where does human design still matter? Model Hosting & ReliabilityHow do we make increasingly complex models reliable and cost-efficient in production? AI Agent OrchestrationWhat does coordination between multiple agents actually look like, and how do we design systems that produce useful emergent behaviour? Meta Prompting for Code GenerationWhich meta-prompting techniques meaningfully improve code quality, structure, and maintainability? The event is deliberately curated for people who are actively building in software and AI, so the conversations stay technical, practical, and useful. If you are not currently hands-on in full-stack, ML, or AI development, this one may not be the right fit. Doors close at 6:30 PM sharp. About your hosts Merantix AI Campus: In the heart of Berlin, the Campus brings together 80+ AI teams and hosts 300+ events a year. Part of Merantix, it is a meeting point for founders, engineers, researchers, operators, industry leaders, and investors building the next generation of AI infrastructure and applications. Hacker Room: A four-month residency at the AI Campus for technical builders working deeply on AI projects. It brings together engineers and researchers developing beyond the API layer in a collaborative envi

via Luma
Add to calendar
⋯
MON 23Nov
Mon 23 Nov 2026, 18:30 Berlin LSE Generate Events

AI is entering its deployment era... As AI models become increasingly powerful and accessible, the real challenge is making them work at scale. BCG estimates that 70% of successful AI transformation efforts depend on people, processes and organisational change - not technology. So what does it actually take to turn AI capabilities into measurable business impact? AI ambition meets business impact: join LSE Generate and BCG X in Berlin for an evening with Sina Stöhr, Partner in BCG’s Berlin office. BCG X is Boston Consulting Group’s tech build and design unit, bringing together more than 3,000 technologists, data scientists, designers and entrepreneurs. What we’ll explore Drawing on real-world examples of AI transformation, we’ll explore: Beyond the pilot: Why promising AI initiatives fail to scale. Rethinking workflows: Why AI adoption requires more than new tools. Delivering impact: How leading companies turn AI into measurable productivity gains. Expect practical insights, an interactive discussion and the opportunity to connect with Berlin’s entrepreneurial and tech community. We can't wait to see you there!

via Luma
Add to calendar
⋯
Same community

More from Daytona

MON 23Nov
Mon 23 Nov 2026, 10:00 Corgi Cafe Corgi London

Join Daytona AI × Corgi Insure for breakfast and brunch at Corgi Cafe in London! We’re bringing together founders, builders, engineers, and tech people for good food, coffee, and conversations with people building what’s next. Daytona builds secure infrastructure for AI agents to run code. Its sandboxes give agents isolated environments to execute tasks and work with files and tools. This helps developers build and scale AI applications. Corgi Insure We’re a full-stack insurance company for businesses, and we’re changing the entire financial industry. Meet someone new, share what you’re working on, and enjoy a morning with London’s tech community. Come hungry and thirsty!

73 going via Luma
Add to calendar
⋯
TUE 24Nov
Tue 24 Nov 2026, 18:00 London Daytona London

An event dedicated to exploring all things AI Engineering! Event partner: Encode Club ​Agenda ​​​​​🕒 6:00 pm – 6:30 pmGathering and Opening Remarks 🎤 Juraj Stefanic, Technical Content Engineer at Daytona ​​​​​​​🕒 6:30 pm – 6:40 pmTalk "Give the Model a Computer: The One Thing Every AI Agent Framework Agrees On"​ 🎤 Mislav Ivanda, DeEx Engineer at Daytona ​​​​​​​​Outline: Building an agent is easy. Deciding where its code runs is the part that follows you to production. This talk comes from a year of building Daytona integrations across the agent ecosystem: LangChain, CrewAI, Google ADK, Mastra, Pydantic AI, the OpenAI Agents SDK, and a long tail behind them. Integration after integration, the same pattern kept surfacing. Frameworks that agree on nothing, not even the language, not the mental model, not who controls the flow, all converge on one identical primitive: give the model a computer. We'll trace why. Every framework ends up facing the same question: where does the model's code actually run? Only three answers exist, and two of them stop holding once real users show up. That's why the past year went the way it did, with frameworks deleting their own code interpreters rather than defending defaults they couldn't. And that's why the computer keeps growing: first a tool call, then the place the agent lives, then a thousand machines at once. You'll leave with one rule: pick the boundary before the framework. Frameworks are opinions. The boundary is a commitment. ​🕒 6:40 pm – 6:50 pmTalk "How Replit uses sandboxes" 🎤 Raouf Chebri, Developer Relations Engineer at Replit ​​​​​​​​Outline: In this talk, we’ll go through Replit’s new capabilities and explore how sandboxes allow for secure work and development. ​🕒 6:50 pm – 7:00 pmTalk "Stop Registering, Start Linking!" 🎤 Sam Bellen, Principal Developer Advocate at Auth0 | Okta ​​​​​​​Outline: Moving MCP Auth from Dynamic Client Registration to Client ID Metadata Documents AI agents need to connect to

321 going via Luma
Add to calendar
⋯
WED 25Nov
Wed 25 Nov 2026, 18:00 Paris Daytona Paris

An event dedicated to exploring all things AI Engineering! Event partner: Replit ​Agenda ​​​​​🕒 6:00 pm – 6:30 pmGathering and Opening Remarks 🎤 Juraj Stefanic, Technical Content Engineer at Daytona ​​​​​​​🕒 6:30 pm – 6:40 pmTalk "Give the Model a Computer: The One Thing Every AI Agent Framework Agrees On"​ 🎤 Mislav Ivanda, DeEx Engineer at Daytona ​​​​​​​​Outline: Building an agent is easy. Deciding where its code runs is the part that follows you to production. This talk comes from a year of building Daytona integrations across the agent ecosystem: LangChain, CrewAI, Google ADK, Mastra, Pydantic AI, the OpenAI Agents SDK, and a long tail behind them. Integration after integration, the same pattern kept surfacing. Frameworks that agree on nothing, not even the language, not the mental model, not who controls the flow, all converge on one identical primitive: give the model a computer. We'll trace why. Every framework ends up facing the same question: where does the model's code actually run? Only three answers exist, and two of them stop holding once real users show up. That's why the past year went the way it did, with frameworks deleting their own code interpreters rather than defending defaults they couldn't. And that's why the computer keeps growing: first a tool call, then the place the agent lives, then a thousand machines at once. You'll leave with one rule: pick the boundary before the framework. Frameworks are opinions. The boundary is a commitment. ​🕒 6:40 pm – 6:50 pmTalk "Faster, Safer Agentic Workloads with NVIDIA Vera and OpenShell" 🎤 Asma Farjallah, Senior AI Developer Technology Engineer at NVIDIA ​​​​​​​Outline: Asynchronous RL post-training overlaps rollout generation with policy updates, cutting GPU idle time at the cost of some off-policy staleness. But agentic rollouts add CPU- and network-bound steps whose latency can still bottleneck GPU utilization. We walk through the asynchronous post-training loop and highlight the CPU-boun

255 going via Luma
Add to calendar
⋯
26 NovIn 4 days
Register →