Yohei Profile picture
Sep 1 12 tweets 4 min read Twitter logo Read on Twitter
Introducing BabyFoxAGI 👶🦊🤖

Newest mod of @babyAGI_ with:

🔂 Self-improving task lists (FOXY method)
💬 Novel Chat UI w parallel tasks
🛠️ New skills (DALLE, Airtable, etc)
📄 It’s own README

Breakdown, Github, Replit 👇
BabyFoxAGI is mod of BabyElfAGI, in a series of mods w the naming of Baby<animal>AGI in alphabetical order:

🐝Bee, 🐱 Cat, 🦌 Deer, 🧝 Elf, 🦊 Fox

You can find the thread introducing BabyElfAGI here: x.com/yoheinakajima/…
🔂 Self-improving task lists (FOXY method)

By storing a final reflection at the end, and pulling the most relevant reflection to guide future runs, BabyAGI slowly generates better and better tasks lists.

Described more in this thread: x.com/yoheinakajima/…
💬 Novel Chat UI w parallel tasks

You can chat w BabyAGI! We have an experimental UI where the chat is separate from the tasks/output panel, allowing you to request multiple tasks in parallel.

(this video has sound, so 🔊sound on!)
x.com/yoheinakajima/…
The Chat UI can use a single skill quickly, or chain multiple skills together using a tasklist.

The latter is what you formally know as BabyAGI.

I have not yet added streaming of BabyAGI progress to the UI (much needed).
Dev note:

What was previously in has moved to , which has an additional function to execute just one skill.

The new houses the back-end functions for the chat UI, and connections with BabyAGI.main.py
babyagi.py
main.py
🛠️ New skills (DALLE, Airtable, etc)

Some fun new skills:

🎨 DALLE skill with prompt assist
🎶 Music player w Deezer
📊 Airtable search (add your own table/base ID)
🔍 Startup Analyst (example of beefy function call as a skill)
📄 It’s own README

I know BabyAGI hasn’t been documented well, and the GitHub is not organized well. This is my attempt at helping a bit more than usual… Image
🐜 Bugs!

I fell behind on work, so I’m pushing this out a bit before I’m really proud of it. Just think of it like fun puzzle to solve if it breaks 🧩
⚙️ Replit

On @Replit, I push each mod as it’s own Repl, so just fork it and add your openai key as a secret called OPENAI_API_KEY, etc.

Here’s the Replit: replit.com/@YoheiNakajima…
⚙️ GitHub

Quick Backstory: I’ve been modding the original BabyAGI instead of working off of the one people contributed to, so my mods are in the “classic” folder.

Here’s the direct link to BabyFoxAGI folder: github.com/yoheinakajima/…
And here is the blog post version of this tweet thread:

As a quick reminder, BabyAGI and it's mods are meant as templates for devs to build upon, not a complete solution.

Hope you enjoy! Would love to hear questions, comments, and ideas :)yoheinakajima.com/introducing-ba…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Yohei

Yohei Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @yoheinakajima

Jul 31
Introducing the "FOXY method" 🦊

Our new approach to self improving auto agents, introduced in the next mod of @babyagi_.

Dig in shall we? 👇 Image
How it works:

With FOXY (Final Output eXamination from "Yesterday"), we do a final reflection on the output of each run, and use this to guide future runs, pulling most relevant reflection using a similarity search, paired with a decay mechanism to prioritize recent reflections.
Here's a simplified version of what this looks like.

In this example, we run the same objective twice. The second task list is improved based on notes from the final reflection of the first run. Image
Read 9 tweets
Jul 10
Meet BabyElfAGI!

Biggest update to the OG @babyAGI_, finally broke out into multiple files:

🛠️ Skills Class allows for easy skill creation
📝 Dynamic Task List example w vector search
🔍 Beta Reflection Agent
🖇️ Can read and write own code (yes it can write new skills and task… https://t.co/mN6jHZydwqtwitter.com/i/web/status/1…
Skills Class

New “Skills” (prev called Mini Agents) are what the task execution agent uses to complete tasks. Enabled in main files handles APIs centrally.

Each skill can be as simple as a simple API call, or a long script w many functions.
New Skills Template

Create easily by simply adding a file in the “skills” folder following our template.

In the template, define the name, description, and required API keys. Description is provided to task creation agent to decide when to use the skill.
Read 16 tweets
May 27
I get asked these often, so thought I’d write up a thread.

Where are we with autonomous agents? What can they do? Should we use one?

My thoughts 👇
A general autonomous agent, that can be given any reasonable objective and accomplish it well… well, we’re far from that. (1~1000 weeks)

Don’t expect to use one today or tomorrow.
In the meantime, if you’re looking for results today, you’re much better off “hand crafting” autonomous agents.

By this, I mean writing detailed prompts and chaining them together in a logical manner.

You can still connect these to APIs or task lists and they’ll run… twitter.com/i/web/status/1…
Read 13 tweets
May 26
testing latest @babyAGI_ mod...

"Look up AI startups, present 5 to the user to have them pick one, and then do further research and provide an investment memo on that startup." Image
searching and scraping... Image
lots of startups found... ImageImage
Read 8 tweets
May 13
Meow!!! 👶🐱🤖 Check it:

OG @babyAGI_ mod #3 - BabyCatAGI

- Higher completion of objectives
- Lower errors
- Faster (GPT4 task creation runs once)
- Hand-crafted Mini agent as tool

✨~300 lines of code

Let’s dig in 👇 Image
As a quick recap, OG @babyAGI_ is the original commit, combining three agents in a loop (task execution/creation/prioritization), only using GPT-3, and designed to never stop.

~105 lines of code.
BabyBeeAGI, our first OG mod introduced:

- a powerful task manager (combining creation/prioritization)
- task dependencies (pulling results from a defined task)
- tools (search, scrape, text-completion)
- objective completion

https://t.co/0H9SC2xVBM
Read 12 tweets
Apr 30
Introducing BabyBeeAGI 👶🐝🤖

A buggier, slower, more powerful mod of OG @babyAGI_ at ~300 lines of code.

✅ Powerful Task Manager
➡️ Task serialization
📋 Local task queue
⚙️ Tools!
🔚 Stops! (usually)
😔 Requires GPT-4

"Paper", Code, & more 👇 Image
Biggest difference is combining the task creation agent and task prioritization into one task manager agent.

We also added task serialization, tools, and tracking complete/incomplete tasks all in the task manager.

Even with GPT-4 we're pushing the limit.

Compare the prompts: Image
BabyAGI was a framework designed for never ending objectives. BabyBeeAGI is designed to stop after completing a handful of tasks.

This means a local task queue variable works fine.

Task dependency is used to pass results between relevant tasks. Image
Read 12 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(