criticality_score VS AutoGPT

TL;DR: I could extend the Criticality Score algorithm with usage metrics from Ecosyste.ms API and apply it to all open source accounts under the Open Collective, so we have a new ranking now! I also made it possible to change the weights of each parameter so that you can try the algorithm by yourself.

As mentioned in the description, the score is based on the OpenSSF criticality score. I dropped some of the features that are difficult to get from GitHub due to crawl limits, as well as changing some weights.

I am doing some research based on the criticality scores assigned by this project to different technologies: https://github.com/ossf/criticality_score

LF OpenSSF "criticality score" for 100,000 Github repos, https://github.com/ossf/criticality_score & https://docs.google.com/spreadsheets/d/1uahUIUa82J6WetAqtxCM...

> Generate a criticality score for every open source project. Create a list of critical projects that the open source community depends on. Use this data to proactively improve the security posture of these critical projects ... A project's criticality score defines the influence and importance of a project. It is a number between 0 (least-critical) and 1 (most-critical). It is based on the following algorithm by Rob Pike

Top 20 projects:

> node, kubernetes, rust, spark, nixpkgs, cmsSW, tensorflow, symfony, DefinitelyTyped, git, azure-docs, magento2, rails, ansible, pytorch, PrestaShop, framework, ceph, php-src, linux

For more information, please check the Criticality Score repo itself.

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.