I built PocketFlow! 100-Line LLM framework to Let Agents Build Agents for You

*Summary:* Learn how to let large language model agents, like Cursor AI, build agents for you using just 100 lines of code: (1) What Pocket Flow is—a minimal large language model framework in 100 lines. (2) The backstory behind Pocket Flow. (3) How to set up Cursor AI with Pocket Flow. Links *Pocket Flow:* https://github.com/The-Pocket/PocketFlow *Cursor rule file:* https://github.com/The-Pocket/PocketFlow/blob/main/.cursorrules *Cookbook:* https://github.com/The-Pocket/PocketFlow/blob/main/cookbook/pocketflow_demo.ipynb *The origin of Pocket Flow*: https://github.com/Cocoon-Data-Transformation/cocoon/blob/main/cocoon_data/workflow.py *Outline:* 0:00 Introduction 0:47 What is Pocket Flow 2:00 Where does Pocket Flow come from 4:10 Demo with Cursor AI 8:58 Conclusion *Social media:* X: https://x.com/ZacharyHuang12 LinkedIn: https://www.linkedin.com/in/zachary-h-23aa37172/ Github: https://github.com/zachary62 Discord: https://discord.com/invite/hUHHE9Sa6T Medium: https://medium.com/@zh2408 Substack: https://zacharyhuang.substack.com/ *About Me:* 👋 I'm Zach, an incoming researcher at Microsoft Research AI Frontiers. I currently work on LLM Agents & Systems. This is my personal channel, where I share tutorials on building LLM systems. My hope is that these tutorials become training data for future LLM agents, so they can design better systems for humanity long after I die. Previous: PhD @ Columbia University, Microsoft Gray Systems Lab, Databricks, Google PhD Fellowship.