Open Source Summit Korea 2026

Recently, LLMs have changed the landscape of security issues in open source software in a radical way. This talk goes into the problems that all open source projects are having with this, and how to use the enemy's resources against them to solve the problem.

Modern AI agents are only as useful as what they can remember. Behind every agent that recalls a user, holds a session, or retrieves context sits a data layer that has to be fast, durable, and portable across the places the agent runs. That memory layer is becoming critical infrastructure, and how it is built and governed determines whether teams stay in control of their own systems or inherit the constraints of whoever owns the layer beneath them. This talk examines the technical problem of stateful memory for AI agents at low latency and scale: the architectural patterns for session state and vector retrieval, the trade-offs between them, and why the licensing and governance of the data layer matter as much as its performance. Valkey, a community-governed key-value datastore under the Linux Foundation, serves as a case study in how these challenges can be met in the open.

Open source has been the single most powerful force democratizing AI—taking capabilities that might otherwise be confined to a handful of well-resourced labs and putting them within reach of researchers, developers, and IT operators everywhere. But the relationship runs both ways: as AI systems increasingly write and contribute code, they are reshaping the open-source ecosystem itself—straining how we manage a rising tide of machine-generated contributions and how we secure code in an era when both attackers and defenders are AI-augmented. In this keynote, I make the case for why open models and open technologies like PyTorch, vLLM, and llm-d are critical enablers for enterprises and governments seeking greater control and flexibility over their AI, and I highlight the technical innovation making this possible. I close by arguing that we have a real opportunity to turn this two-way street into a virtuous loop—building AI that accelerates and secures open source even as open source accelerates AI.

As AI matures from a novelty into a strategic asset, 79% of organisations now prioritise sovereignty to mitigate vendor lock-in and secure critical data. Despite this, the market remains paralysed by a paradox: while open models have achieved performance parity with proprietary systems at a fraction of the cost, they remain massively under-utilised due to perceived friction and trust gaps.

This session dissects this market inefficiency, with insights from LF Research revealing how closed-source dominance is often driven by inertia rather than superior capability. We will explore how to operationalise true independence by rejecting "open-washing" in favour of rigorous frameworks that demand full model completeness: verifying everything from training data to weights. Join us to learn how to transition from renting black-box APIs to architecting a transparent, reproducible, and economically superior AI stack.

As AI agents become increasingly capable of generating code and executing complex workflows, their use in research is still limited by concerns about rigour and reproducibility. This session introduces ado, an open-source framework that brings structure to agent-driven scientific experimentation.

ado defines schemas for the core elements of a discovery process: the problem space and how to explore it. Agents iteratively propose and refine experimental campaigns as validated configurations based on these schemas, while ado handles execution. This separation of research intent from execution constrains agents to focus on the research task, reducing hallucinations and the need to write boilerplate code. Combined with a set of agent skills for formulating problems, creating and running experiments, and analysing their results, ado provides a framework for end-to-end agent-driven discovery workflows.

Whether you are an experienced researcher or new to computational experimentation, this talk presents a practical model for integrating AI agents into research workflows while keeping experimentation structured, transparent, and reproducible.

"Let’s be real: My AI has dementia."
"Vibe-coding in real: Me and My AI is stupid"
Welcome to the "Vibe Coding" era, where anyone can prompt their way to complex code. But as a 17-year-old developer who "bullied" LLMs to build a custom Linux Based OS (MaruxOS) from scratch, I’ve seen the ugly truth: AI is a brilliant assistant, but a chronic liar with a 5-minute memory.
In this session, I expose the messy reality of AI-native development. I’ll share how I battled "Contextual Dementia"—where AI forgets my ARM64 architecture mid-patch—and survived "Mindless Yes-Clicking Syndrome," where a single trusted prompt almost nuked my entire glibc.
Key Takeaways:
The Hallucination Hunter: Sniffing out AI’s "confident bullshit."
The Dementia Doctor: Managing AI’s memory loss to maintain architectural integrity.
The Final Decider: Moving beyond the "Yes-Clicking" trap to take true technical ownership.
AI might be writing the code, but only a real engineer can stop it from burning the house down.

Most open-source AI demos stop at a chatbot, but real users want agents that can work with private files, call tools, and run close to their important data without sending everything to the public cloud.

This talk shows a practical reference architecture for private agent workflows on a single-node K3s-based personal cloud, including local model serving, private knowledge bases, app sandboxing, secure remote access, and multiple GPU allocation modes for competing AI workloads.

Using an open-source personal cloud OS as a case study, I will share what works, what breaks, and which design choices matter when you try to make local AI usable by developers, creators, and small teams rather than just homelab experts.

As organizations explore the Model Context Protocol (MCP), many of the early conversations naturally happen around AI tooling, integrations, and experimentation. At the same time, MCP may also raise questions that are familiar to Open Source Program Offices (OSPOs) and related teams or professionals with open source management experience, including governance, contribution strategy, standards engagement, and cross-functional coordination

This talk reflects on what organizations might gain by bringing those perspectives into MCP discussions earlier, as well as into their broader Agentic AI strategy. Rather than treating MCP only as a technical AI topic, the session will explore it as an area where open source process knowledge may also add value. Attendees will leave with ideas for how OSPOs can contribute to MCP adoption in practical, collaborative, and organization-aware ways

Agentic search lets you ask in Natural Language and have OpenSearch plan and execute retrieval. The Query Planner re-writes Natural Language to OpenSearch DSL using SOTA LLMs. This works amazingly well but not without important limitations:

1/ The biggest factor is added latency for remote inference. eCommerce Search demands sub-100ms response times. Even the best results when slow lead to search abandonment.
2/ We'll demo overcoming latency by hosting SLMs locally within OpenSearch nodes using vLLM/Ollama. This is faster & cheaper, but SLMs suffer quality decline in query re-writes. We'll explore fine-tuning with domain-specific data—proving fine-tuned SLMs beat SOTA LLMs.
3/ Relevance remains generic even with Agentic Search. We'll show how to improve it using user and business contexts with hybrid search and reranking.

This hands-on talk covers:
1/ Search Latency with Remote Inference
2/ Locally hosting SLMs using vLLM/Ollama
3/ Agentic search with SLM Local Inference
4/ Improving relevance with user and business contexts
5/ Fine-tuning SLMs for domain-specific query re-writing via Axolotl/LLaMA-Factory