finds.dev← search

// the find

coleam00/ai-agents-masterclass

★ 3,435 · Python · MIT · updated Jan 2025

Follow along with my AI Agents Masterclass videos! All of the code I create and use in this series on YouTube will be here for you to use and even build on top of!

A YouTube tutorial series companion repo where each numbered folder corresponds to a video on building AI agents with LangChain, LangGraph, and related tools. It's for developers who learn by following along with video content rather than reading documentation. The code exists to support the videos, not to be a reusable library.

Covers a reasonable breadth of real integration targets (Asana, Google Drive, n8n, Supabase, local LLMs via Ollama), so you get past toy examples. The numbered folder structure makes it easy to jump to a specific episode without wading through everything. Includes the LangGraph multi-agent pattern (episode 7+) which is the part that actually matters for anything non-trivial. The local-ai-packaged folder with docker-compose is genuinely useful for getting Ollama + n8n + Flowise running without manual setup.

No tests anywhere — this is demonstration code, not production code, and adopting any of it as-is will bite you. Dependency versions are pinned loosely or not at all across different requirements.txt files, so running an older episode often means broken installs as the LangChain API surface keeps changing. The last push was January 2025 and LangChain/LangGraph have had multiple breaking releases since, meaning a non-trivial fraction of the code probably doesn't run without downgrading. Everything is a single flat script per episode with no separation of concerns, which works for tutorials but teaches bad habits if you internalize the structure.

View on GitHub →

// want more like this?

We dig through GitHub every week and send a few repos picked for what you actually care about — each with an honest take like this one.

Get finds in your inbox → Search again →