https://amineelfarssi.github.io/tags/langgraph/Recent content in LangGraph on Amine El FarssiHugo -- gohugo.ioen© 2026 Amine El FarssiMon, 02 Mar 2026 00:00:00 +0000https://amineelfarssi.github.io/projects/ai-agents/Mon, 01 Jan 0001 00:00:00 +0000https://amineelfarssi.github.io/projects/ai-agents/<p><span class="flex cursor-pointer"> <span class="rounded-md border border-primary-400 px-1 py-[1px] text-xs font-normal text-primary-700 dark:border-primary-600 dark:text-primary-400"> AWS Bedrock </span> </span> <span class="flex cursor-pointer"> <span class="rounded-md border border-primary-400 px-1 py-[1px] text-xs font-normal text-primary-700 dark:border-primary-600 dark:text-primary-400"> LangGraph </span> </span> <span class="flex cursor-pointer"> <span class="rounded-md border border-primary-400 px-1 py-[1px] text-xs font-normal text-primary-700 dark:border-primary-600 dark:text-primary-400"> Python </span> </span> <span class="flex cursor-pointer"> <span class="rounded-md border border-primary-400 px-1 py-[1px] text-xs font-normal text-primary-700 dark:border-primary-600 dark:text-primary-400"> AgentOps </span> </span> <span class="flex cursor-pointer"> <span class="rounded-md border border-primary-400 px-1 py-[1px] text-xs font-normal text-primary-700 dark:border-primary-600 dark:text-primary-400"> Production </span> </span> </p>https://amineelfarssi.github.io/blog/multi-agent-startup/Mon, 02 Mar 2026 00:00:00 +0000https://amineelfarssi.github.io/blog/multi-agent-startup/<div class="lead text-neutral-500 dark:text-neutral-400 !mb-9 text-xl"> Luminar has 173 source files, 21,586 lines of production code, 43 API endpoints, and 155+ tests. It was built almost entirely by AI agents. Here&rsquo;s the team structure, the workflow, and the honest truth about what breaks. </div> <h2 class="relative group">The Team <div id="the-team" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#the-team" aria-label="Anchor">#</a> </span> </h2> <p>I didn&rsquo;t want generic agents. I wanted specialists — each with a clear domain, sharp ownership boundaries, and a persona that shapes how they approach problems.</p>https://amineelfarssi.github.io/blog/agentic-frameworks-comparison/Sun, 01 Feb 2026 00:00:00 +0000https://amineelfarssi.github.io/blog/agentic-frameworks-comparison/<div class="lead text-neutral-500 dark:text-neutral-400 !mb-9 text-xl"> Building production AI agents requires choosing the right framework. This analysis examines <strong>pi-agent-core</strong> (OpenClaw&rsquo;s runtime), <strong>Google ADK</strong>, <strong>AWS Strands</strong>, <strong>CrewAI</strong>, <strong>LangGraph</strong>, and <strong>Pydantic AI</strong> across critical dimensions: sessions, memory, protocols, agent loops, and replay support. </div>