Build Your Own Open-Source Claude Code With Local LLMs - Daniel Oh, Red Hat

Join us at AGNTCon + MCPCon NA 2026, the premier event for people building, operating, researching, or supporting agent systems. Where developers, architects, and AI practitioners come together to explore the latest in agentic AI, tool protocols, and production-ready MCP architectures. Learn more here: https://events.linuxfoundation.org/agntcon-mcpcon-north-america/ Build Your Own Open-Source Claude Code With Local LLMs - Daniel Oh, Red Hat AI coding assistants are becoming part of everyday development, but many enterprises cannot send source code, internal APIs, or project context to external services. They need the productivity of coding agents while keeping models, repositories, prompts, and actions under their control. In this session, we’ll show how to build an open-source, Claude Code-like assistant using local or privately hosted LLMs, Models as a Service, OpenCode, and AI guardrails. Developers will be able to explore a codebase, generate changes, review explanations, and trigger controlled actions without exposing sensitive data. We’ll also cover the guardrails needed for real use: secrets protection, data leakage checks, unsafe command blocking, insecure code detection, and policy-based action control. You’ll leave with a practical blueprint for building a private, secure coding assistant that improves developer productivity without compromising trust, privacy, or compliance.