ambler-m3u-downloader VS PocketFlow

I'll continue experimenting with this approach, but I can already see how useful it will become when needing to automate simple tasks. Gemini CLI has already made me a handy application to download URLs from an m3u file which is a great companion to an Chrome Extension Gemini CLI built for me a while ago. All I need now is more ideas to test the approach with.

git submodule add https://github.com/The-Pocket/PocketFlow.git vendor/pocketflow

> Some people call this "the agentic loop." Call it what you want, you can write it in 100 lines of Python

That description sounds a lot like PocketFlow, an AI/LLM development framework based on a loop that's about 100 lines of python:

https://github.com/The-Pocket/PocketFlow

(I'm not at all affiliated with Pocket Flow, I just recall watching a demo of it)

I wanted to share a project I've been working on called Flyt https://github.com/mark3labs/flyt (Norwegian for "flow", pronounced "fleet").

I was inspired by the Python package Pocket Flow https://github.com/The-Pocket/PocketFlow and wished for something similar in Go. So I built Flyt, a lightweight workflow framework that lets you compose complex workflows from simple, reusable nodes.

Key features:

I recently came across an interesting project called PocketFlow, which presents a minimalistic approach to building workflows that incorporate large language models. It is originally written in Python, a language I have never really used, so I attempted to port it to Kotlin to better understand how it works. As I progressed it became clear the project was simply a glorified state machine and it could be simplified even further. The result was Ambler: a very simple function and a very simple class definition that allow you to express a program as a series of steps that update the current state and pass it on to the next step.

The 100 lines: https://github.com/The-Pocket/PocketFlow/blob/main/pocketflo...

This brings us to the most critical, and often botched, aspect of agent design: context management. Think of it as the warrior's Cognitive Backpack. In our PocketFlow framework, this is the simple shared dictionary that each Node reads from and writes to. The naive approach is to stuff everything inside. Imagine loading the entire dungeon map, every monster's stat block, every rumor of treasure, and the history of the last three adventurers who failed into the warrior's backpack right at the start. They'd collapse under the weight before they even took their first step.

In this guide, you are the master blacksmith. Using the transparent and powerful PocketFlow framework as your forge, we will teach you how to craft an arsenal of actions that will turn your agent from a clumsy squire into a legendary warrior.

This project is powered by PocketFlow, a tiny but mighty AI framework that makes building this kind of intelligent, looping agent incredibly straightforward. Forget vector databases and manual updates. Let's build a chatbot that just works.

This system is built using Pocket Flow, a 100-line minimalist framework for building LLM applications. What makes Pocket Flow special isn't just its compact size, but how it reveals the inner workings of AI application development in a clear, educational way.