loopgpt VS AutoGPT

So we thought it would be a good idea to create a framework that makes use of LoopGPT agent's memory and custom tooling capabilities. Let's jump right into the new features of this framework.

LoopGPT Modular Auto-GPT Framework (https://github.com/farizrahman4u/loopgpt)

We just added Azure OpenAI support on our modular reimplementation of Auto-GPT: LoopGPT. And I think it's much easier to setup using our python API because you can just use the copy-paste that you can get from "View code" on the Chat Playground on Azure. Here's the whole snippet that you need to use.

I suggest using LoopGPT, a GPT-3.5 friendly, modular re-implementation of Auto-GPT (this is self-promotion, I am a co-author FYI :). We have full state serialization which means you can save your agent state completely and start right from where you left off. To get started just do

As another MLE, who's working on an Auto-GPT inspired project, I want to say that I totally understand this technology (atleast with GPT-3.5) is not great. This is why we focused on building a better codebase, which is extensibile, modular and is just an overall more "Pythonic" reimplementation of Auto-GPT rather than trying to claim to be perfect. Although, I must mention that people have had better results with LoopGPT with both GPT-3.5 and GPT-4, and we don't even have GPT-4!

I suggest you try LoopGPT - It works better on GPT-3.5 according to many users. We have a nice little discord too where you can post any issues: https://discord.gg/rqs26cqx7v

Glad you got it figured out. Please also try out LoopGPT if you can - it works better with GPT-3.5

This 100%. Also, AutoGPT is not the best option when you want to add more capability, LoopGPT is as it has a framework to easily add more capabilities (called tools).

We recently released a GPT-3.5-friendly reimplementation of Auto-GPT, a "Pythonic" modular framework called LoopGPT that supports adding custom tools. Our first-time users tell us it produces better results compared to Auto-GPT on both GPT-3.5 as well as GPT-4.

Define agency. Does AutoGPT or BabyAGI fit the definition?

This leap is evident in projects like BabyAGI and AutoGPT, showcasing how such agents can prioritize and execute tasks based on a pre-defined objective and the results of previous actions, such as sales prospecting or ordering pizza.

A system and a user message are constructed from the task given by the user in code and passed to the LLM as input.

A: How much do you know? If you can easily read code (in this example Python, but this will still benefit anyone who can read code), you should check out Auto-GPT. If you are looking to explore different options, check out this doc on AI Agents.

Also I think most agents I have seen have implemented some form of long-short term memory. Why does it say autogpt doesnt support it? https://github.com/Significant-Gravitas/Auto-GPT/tree/master/autogpts/autogpt/autogpt/memory

In my newest experiment, I try out MetaGPT, which is supposed to be better than AutoGPT according to MetaGPT's paper.

In my opinion the most interesting Agents: Auto-GPT Github: https://github.com/Significant-Gravitas/Auto-GPT BabyAGI Github: https://github.com/yoheinakajima/babyagi Voyager Github: https://github.com/MineDojo/Voyager / Paper: https://arxiv.org/abs/2305.16291 I would also add: ChemCrow: Augmenting large-language models with chemistry tools Github: https://github.com/ur-whitelab/chemcrow-public/ Paper: https://arxiv.org/abs/2304.05376

Check out the new Re-Arch README and ARCHITECTURE_NOTES.