Open Source Summit Korea 2026

As Generative AI and Agentic AI continue to evolve, cyberattacks have become increasingly automated. With hundreds of new CVEs disclosed every day and AI-powered attacks are automated in zero-hour, traditional security and patch management approaches have reached their limits.

This session explores how organizations can build a lightweight hardened infrastructure and a trusted Zero-CVE environment with Red Hat AI on a proven platform that leverages the strengths of the open source ecosystem. It also examines the need for autonomous defense systems and approaches to implementing them, enabling real-time threat response while maintaining infrastructure stability through controlled AI-driven automation.

When enterprises bring AI into real-world operations, reliability challenges extend far beyond hallucinations and response accuracy. Document structure and meaning can be lost during processing, retrieval may fail to provide sufficient grounding, and models may violate business rules or operational constraints. As agents connect to enterprise systems, additional risks emerge, including unauthorized tool calls and actions that are difficult to trace or audit.
These challenges cannot be addressed by adding a guardrail at the final stage. Reliability must be designed across the entire workflow, from document understanding and retrieval to reasoning, generation, and execution.
This session presents an open-source reference architecture that combines document representation with Docling and DocLang, grounded retrieval and reasoning with OpenRAG and Granite, requirement-driven generation and validation with Mellea, and controlled, observable tool integration with ContextForge.
 

Large Language Models (LLMs) are widely used to search, summarize, and generate answers. They are powerful, but results are not always stable and can be difficult to verify.

Many systems use Retrieval-Augmented Generation (RAG) to connect LLMs with external data. This helps, but does not fully solve the problem. The same question can produce different answers depending on the model or context, making knowledge hard to manage.

This raises a simple question: where should knowledge be managed?

A similar issue exists in software supply chains. SBOM (Software Bill of Materials) makes components and relationships visible, but is often treated as static data.

Based on hands-on experience designing graph-based knowledge systems, this session introduces a design approach: managing knowledge outside LLMs as structured, persistent data.

We discuss lessons from SBOM and how graph-based approaches—using technologies such as SQL/PGQ or GQL—can help understand relationships and trace changes.

The focus is a practical way of thinking for more open and sustainable knowledge practices.

AI agents are quickly moving from prototypes to production systems that manage APIs, tools, and complex reasoning tasks.

Once these systems are deployed, they often act like black boxes, hiding failures, slowdowns, and unexpected behavior.

This session will show you how to add observability to agentic systems with open-source tools and cloud-native tech.

​Brandon and Mostafa will break down the lifecycle of an AI agent, covering prompt execution, tool invocation, memory access, and multi-agent coordination, and demonstrate how to make each stage observable.

Using a practical, architecture-focused approach, they will show how to:

- Trace agent workflows across distributed systems
- Monitor latency and token usage
- Detect anomalies such as hallucinations, tool misuse, and runaway behavior.
- Connect LLM behavior with infrastructure metrics like GPU, container, and network data.

They will also present a complete reference architecture that uses open-source projects including OpenTelemetry (OTel), Prometheus, Grafana, and some new tools for LLM observability.

Attendees will learn practical ways to build transparent and reliable production AI agent systems.

The shift to digital money is accelerating in Korea and globally - central bank digital currency pilots, tokenized deposits, and real-world asset tokenization are moving toward production, stablecoins are gaining regulatory clarity. However, key challenges remain around interoperability, scalability and integration with existing financial systems.

In this panel, Julian Gordon, VP Asia Pacific & Middle East at LF Decentralized Trust, will host a discussion with leaders from Korea’s financial and technology ecosystem on moving from PoC to production-grade digital money infrastructure.

Panelists will share insights from initiatives including CBDC pilots, public-private collaboration, agentic AI integration, and developments in tokenized deposits and assets – exploring how open source decentralized technologies are improving settlement efficiency, programmability and interoperability across platforms and networks.

They will examine the role of open development, governance and standards in building secure, scalable systems. Attendees will gain practical perspectives on architecture, ecosystem coordination and policy shaping the next phase of digital money.

Standard FP8 formats suffer from frequent gradient overflows and heavy reliance on complex Delayed Scaling, which often lead to training instability or suboptimal convergence in large models. This session introduces HiFloat8 (HiF8) — a tapered precision format that offers an alternative approach to managing dynamic range. This "natural" alignment with neural network weight/gradient distributions allows HiF8 to capture high-magnitude outliers without the aggressive scaling required by standard FP8.We explore how HiF8 can works in the training and inference procedure.We will demonstrate the implementation of HiF8 within the ecosystem. They allow developers to evaluate performance of Hif8 on GPUs. Also, we will give an analysis of training stability and final loss parity where HiF8 provides relatively the same accuracy and 1.5-1.7 times GEMM performance than FP16. Finally, we will share insights from our ongoing collaboration on dedicated hardware support for HiF8.

In April 2026, x402 joined the Linux Foundation with over 20 founding members. It is the first payment protocol under open source governance at the Linux Foundation.

x402 activates HTTP 402 "Payment Required," reserved in 1997 but never used. A server responds with 402 and payment terms, the client settles on-chain, the resource is delivered. Apache 2.0, zero protocol fees, chain-agnostic, no single-organization dependency.

Part 1: Why now. Every internet layer runs on open protocols except payments. That breaks when AI agents must pay at machine speed. We map the agentic payment stack and ask: is it open, who governs it?

Part 2: How x402 works. HTTP 402 challenge-response, stateless architecture, one middleware line to gate any API, production deployments today.

Part 3: Bottom-up to foundation. x402 was open-sourced, developers adopted it, major infrastructure providers shipped native support, competing protocols chose to integrate x402 rather than build a rival. Then it moved to the Linux Foundation.

Part 4: What comes next. The protocol is early. Foundation governance changes the signal. We examine what sustained adoption requires.