LangGraph in Production — Build Forge, an Autonomous Coding Agent on LangGraph v1.x

About this course

This is a free, code-first course for Python developers who use LLM APIs and want to master LangGraph — the framework, not just the snippets. Across the series you build Forge, an autonomous coding agent: it takes an issue against a real fixture repo, plans the change, edits files in parallel, runs the test suite in a self-correcting loop, opens a pull request, and waits for your approval to ship — fully persisted, durable, streamed, and evaluated.

Built and verified against LangGraph v1.x (langgraph 1.2.5) with the v1 idioms only — create_agent (not create_react_agent), interrupt(), the Send API, durability modes, the Store, and the Functional API. Every lab lives in the companion repo and runs offline on a laptop (the LLM is stubbed; a real sandboxed pytest is the signal), with the cumulative suite green. No certification gate — this is the definitive, current, production-grade LangGraph course.

Syllabus

1. 01 Why LangGraph? From a While-Loop Agent to a Graph (LangGraph in Production, Module 01) 18 min read Read
2. 02 StateGraph Fundamentals: State, Reducers, Nodes, and Edges (LangGraph in Production, Module 02) 18 min read Read
3. 03 Control Flow: Conditional Edges, Command, and Self-Correcting Cycles (LangGraph in Production, Module 03) 18 min read Read
4. 04 Tools and the Agent Loop: ToolNode, create_agent, and Structured Output (LangGraph in Production, Module 04) 22 min read Read
5. 05 Parallel Work: The Send API, Map-Reduce, and Fan-out/Fan-in (LangGraph in Production, Module 05) 18 min read Read
6. 06 Persistence: Checkpointers, Threads, and Resumable Runs (LangGraph in Production, Module 06) 20 min read Read
7. 07 Human-in-the-Loop: interrupt(), Approval, and Editing the Plan (LangGraph in Production, Module 07) 18 min read Read
8. 08 Time-Travel: State History, Replay, and Forking a Bad Run (LangGraph in Production, Module 08) 18 min read Read
9. 09 Durable Execution, Resilience, and Sandboxing (LangGraph in Production, Module 09) 22 min read Read
10. 10 Long-Term Memory: the Store and Semantic Recall (LangGraph in Production, Module 10) 18 min read Read
11. 11 Streaming: Modes, Tokens, and Real-Time Progress (LangGraph in Production, Module 11) 22 min read Read
12. 12 Subgraphs and Multi-Agent Systems: Supervisor, Swarm, and Handoffs (LangGraph in Production, Module 12) 22 min read Read
13. 13 The Functional API: @entrypoint, @task, and When to Use It (LangGraph in Production, Module 13) 22 min read Read
14. 14 Deploy Forge: LangGraph Platform, the Server API, and Studio (LangGraph in Production, Module 14) 30 min read Read
15. 15 Capstone: Evaluate with LangSmith and Ship Forge v1.0 (LangGraph in Production, Module 15) 25 min read Read
16. 16 Production Readiness and Mastery Review (LangGraph in Production, Module 16) 35 min read Read