Most agent tutorials stop before the hard parts. This one builds them step by step. Deep Agents from Scratch is a five-notebook LangGraph co…

Most agent tutorials stop before the hard parts. This one builds them step by step. Deep Agents from Scratch is a five-notebook LangGraph course for builders who want to understand how advanced AI agents are assembled. It helps you move from a basic ReAct loop to a research-agent workflow by implementing task planning, file-based context offloading, and sub-agent delegation in sequence. Key features: • Progressive notebook path – five lessons build from create_agent to a complete research agent • ReAct foundation – starts with the reason-act loop used as the base for the later lessons • TODO planning – adds status-tracked task lists to organize multi-step workflows and monitor progress • Virtual file system – stores information in agent state with read, write, edit, and list operations for context offloading • Sub-agent delegation – introduces specialized agents, focused tool sets, and parallel work for independent research streams It’s open-source (MIT license). Link in the reply 👇

Related

• Want to run the same harness across multiple interfaces? Try ACP. Deep Agents ships with it out of the box.
• Agent engineering is hard Deep Agents hides a lot of the weird systems complexity, but still gives you more room to customize the harness th…
• LangChains create-agent is a super minimal agent sdk If you want a more batteries included - that’s deepagents Middleware lets you extend bo…
• Deep Agents ship with durable execution out of the box: every agent step is checkpointed, so you get observability, fault tolerance, and hum…

Source: Harrison Chase (X) | 2026-08-31