🚀 What are you going to build with agency-swarm? Excited to see your ideas!💡

BIG PROPS for giving credit where credit is due!

dude you're killing it! One of the few people in the AI agency space here on YT who is actually spitting gold 👌

Hook this up to a few corporate training manuals and that’s it… we can automate “appearing” to be working from home 👍

This looks awesome! Thanks for the shoutout :)

All the way from Singapore,,,, you have a fan and love your stuff Vrsen!

From the little quick test, I’ve created, using your solution, big props to what you’re building.

Absolutely incredible, cant wait to try this out tomorrow. Thanks a lot !!

Great content! Very informative. Loved to hear about others in the field and where ideas originated and what is missing from OpenAI sides for developers!

Wow, this is absolutely awesome, congratulations. You dude elevated yourself.

Awesome tutorial. You are embracing AI & automation at it core.

@vrsen great concept. I've just tried it out and have a few questions 1. Can your tool scroll? In my experiments it can only read the first screen, but cannot scroll or look at additional pages 2. How does it get around CAPT? Seems to stop at this challenge 3. Can we provide guidance/instructions/rules to agents? 4. What are the API endpoints if we don't want to use Gradio? You've almost swayed me from other frameworks. I like the way that you think. Your logic and the way you look at things is similar to my own. You're just a much better coder. Impressive!

Is it possible to use lavva open source model instead of GPT4?

Amazing video bro. I still wonder if you might do a video on FinGPT and fund manager-related AI scripts. For fund managers, research on the economic metrics and timely update global news to fulfill the preferred return for their investors is a pain in the ass but mandatory. If there is an AI swarm system that can do numerical, sentimental and technical analysis and summarize or strategize the investment strategy that will meet with the preferred return for those funds managers that will be Billion dollar market if not Trillions for no joke. But the nature of data output will be extremely time-sensitive.

This definitely looks interesting. I will look further into. Thanks!

I do think we can extend on this with website agent templates for many websites. The templates include navigators so it’s entirely automated just by voice prompting. I see the future where the agent is specifically guiding this way including larger trusted tasks including paying for things just by voice commands. The goal is for the agent to communicate through the guided templates that are premade for individual websites including bubble and Figma.

Hey, great work so far! I've been testing language and vision models on a Mac Mini M1 16GB. From what I see here it is totally possible to run this specific use case on a machine like that. A Mac Mini M2 Pro 32GB is about 2000€, a refurnished 16GB M1 is less than half of that. Those machines are cheap to run and ROI will be quick.

thank you so much for this, absolutely legendary.

Great job! Do you plan to relese installable apps for mac or windows? This may be the best way to monetize for you.

master piece as usual.. I'll like to ask for your help for a project, I'll probably set up an appointment afterward..

Amazing, congratulations brother 🦾💎

I'll check it out and let you know.

Love the content. In looking into using your swarm to manage swarms within it. Think of having entire departments of an oraganization as a swarm. And then a swarm that orchestrates that. Id love to see the ability to introduce other models or local models as an option. Adding something like a memgpt agent or txtai agent to give your agencies less context restraints and more long term memory.

Absolutely brilliant! I am in. From a feasbility perspective, love to see more about the tech debt around a production level deployment and an idea, ty. I'll keep watching and give it a whirl!

Just curious, can we use Gemini Pro?

Awesome stuff! 👍

Incredible. Gonna give it a whirl.

This is amazing automation and is disruptive. Can you please keep your openai GPT current with your improvements and updates? It would be appreciated! I want to automate a boring part of my work that is simple OCR to data entry.

have u considerd LLaVa Arsenii?

Cam it browse Internet and get me information for my academic research on various topics ?

This is why we need to be posting our comments on billboards instead of the internet F society

BEST BROWSING AGENT

do you think opensource multimodal models like llava could make it ?

Yes yes!! Let's go boss!!

Could this be run locally with a model from hugging face, as another method to bring down costs?

how to build query bot ,it should query from the database like mangodb where the data are stored from the application

@vrsen I tried to set this up lastnight and getting some errors in jupyter notebook. Can you help ?

Awesome - will play around a little :-)

I just cloned this project and got it working. It is awesome! In the first demo in the notebook, you give the agent a task and it will perform web searches, pick out relevant pages from the search results, analyze these pages, navigate to other relevant pages, and attempt to complete the task. It's not perfect, it does get stuck sometimes, but it's the best tool I have seen for automated browsing of the Internet. For anyone who is having problems, I suggest that you re-install it because it has been updated in the last few days. Also, feel free to ask me questions and I will answer if I can.

Where should I start with your content man trying get my head around the swarm

How about using Mistral instead of OpenAI to keep it independent and safe?

Thank you for a helpful framework! On github, the notebook code doesn't appear - it shows the message Invalid notebook - 'execution_count' is a required property. I cloned the repo and ran jupyter notebook but the file doesn't appear. Do you know what might be wrong? # edit: just opened it in VSCode

Can it do multiple browsers at the same time , 50+ and connect to a proxy server

dude i was working on the exact same thing lol, i’ll see if i can contribute my fix for the login info soon

What are the pros over CrewAI. Based on one of your other video about AutoGen, I think the ability to scale and avoid internal prompts that cause problems with your agents. What else?

Amazing Video! Also Made a Full Video on How can Ai be used to generate KZfaq shorts. There are some Videos on YT but they have certain limations.

Does it scroll?

🎯 Key Takeaways for quick navigation: 00:00 🤖 *Introduction to Agency Swarm and its Advanced Browsing Capabilities* - Overview of Agency Swarm's advanced web browsing capabilities with GPT-4 vision. - Agency Swarm can perform tasks like clicking links, filling forms, scrolling, and navigating pages. - Announcement of a demonstration later in the video. 00:26 💡 *OAI Widget and QA Testing* - Introduction to the OAI Widget and its QA testing process. - Agency Swarm utilizes two agents: a quality assurance manager and a browsing agent. - Description of an 8-step QA testing process. 01:21 🔐 *Browsing Agent's Login and Task Execution* - Browsing agent's ability to handle login using credentials and solve page navigation issues. - Execution of tasks likecreating a new widget and responding to QA manager's instructions. 02:13 🧩 *Step-by-Step Task Execution and Flexibility* - Importance of step-by-step instructions for efficient task completion. - Flexibility in providing general goals for manager agents to break down. 03:08 🌐 *Origin of GPT-4 Vision-Powered Web Browsing* - Credit to KZfaqr Unconventional Coding for the original GPT-4 vision-powered browsing script. - Discussion of limitations in the original script and improvements in Agency Swarm. 04:03 🚀 *Features and Capabilities of Agency Swarm's Browsing Agent* - Detailed explanation of the browsing agent's features in Agency Swarm. - The browsing agent's ability to interact with web elements using GPT-4 vision. 05:22 🛠️ *Tools and JavaScript Integration for Browsing* - Description of various tools used by the browsing agent and their functions. - JavaScript integration for creating bounding boxes and labels on web elements. 06:14 📝 *Setting Up and Using Agency Swarm* - Guide to setting up and using Agency Swarm. - Steps to create an agent swarm and manage tasks with multiple agents. 07:12 ⚙️ *Configuring the Report Manager and Browsing Agent* - Instructions on configuring the report manager and browsing agent in Agency Swarm. - Emphasis on the manager agent's role in task breakdown and issue resolution. 08:08 🔍 *Comprehensive Reporting and Web Analysis* - Utilization of Agency Swarm for compiling comprehensive reports and web analysis. - Example of creating a report using the browsing agent for web scraping. 09:02 💵 *Cost Analysis and Potential Improvements* - Discussion on the costs of using Agency Swarm and potential improvements. - Anticipation of future features from OpenAI that could enhance Agency Swarm. 10:02 🌟 *Future Plans and Agency Swarm Deployment* - Plans for creating an agency that generates other agencies. - Suggestions for deploying Agency Swarm in various applications. Made with HARPA AI

If I may request, can you make a fullfledge State-of-the-Art Chatbot which leveraging AutoGen+LangChain+GPT-4Turbo+GPT-4-V and related tools to basically do ChatGPT-4 but with our own knowledge? I mean like the real Google Gemini Video Demo + able to upload document

Keep it up.

can you make a video about roadmap to be an AI developer 😊😊❤, very useful video btw

Wow very impressive

Im just curious , what if there a captcha being prompt , are we able to handle that as well ?

cookie xferring mechanism. NOVEL suggestion 🙂

Yo. howd you maKe that badass thumbnail?

Quick question. I was trying to run your notebook example and got the following error. I deleted the settings.json thinking this might be the issue. Any input is much appreciated! openai.BadRequestError: Error code: 400 - {'error': {'message': '1 validation error for Request body -> file_ids none is not an allowed value (type=type_error.none.not_allowed)', 'type': 'invalid_request_error', 'param': None, 'code': None}

Красава!

I'm a Software Test Automation QA, i can try this and add some code to handle popups.

Can it manage my websites and emails

🎯 Key Takeaways for quick navigation: 00:00 🌐 *Introduction to Agency Swarm's GPT-4 powered web browsing* - Agency Swarm uses GPT-4 to browse the web like a human, performing actions such as clicking, filling forms, scrolling, and more. 01:21 🤖 *Demonstration of Agency Swarm in a QA testing scenario* - QA manager instructs the browsing agent through steps, such as logging in, creating a new widget, and sending a test message. - Browsing agent utilizes tools like click element, send keys, and select drop-down to perform tasks with GPT-4 vision. - QA manager receives feedback on each step, ensuring smooth execution of the testing process. 03:08 🛠️ *Evolution of GPT-4 vision-powered web browsing and introduction to Agency Swarm* - Acknowledgment of Unconventional Coding's script as the origin of the idea. - Comparison of limitations in the original script and how Agency Swarm overcomes them. - Explanation of GPT-4 vision tools in Agency Swarm, making it fully Python-based and expandable. 04:29 🧠 *Overview of tools in Agency Swarm's browsing agent* - Presentation of seven tools in the browsing agent, including read URL, scroll, go back, click element, analyze content, send keys, and select drop-down. - Tools utilize GPT-4 vision for various actions on web pages. - JavaScript is used to create bounding boxes and labels directly in the browser window. 06:14 🛠️ *Steps to create your own Agent Swarm with browsing capabilities* - Installation process involving Anaconda, cloning the Agency Swarm repo, creating a Conda environment, and installing Jupyter. - Instructions for running examples and testing OAI Widget, emphasizing user credentials in task descriptions. - Guidance on creating an agent swarm with a focus on the report manager and browsing agent. 08:08 💼 *Demonstration of creating a report using Agent Swarm* - Report manager breaks down tasks and communicates with the browsing agent to analyze web pages. - Tasks include analyzing Google search results, LinkedIn profile, AI Accelerator Institute page, and GitHub profile. - The report manager compiles a comprehensive report based on the information gathered. 09:32 💡 *Insights into cost considerations and future improvements* - Discussion on costs associated with scraping data using Agent Swarm. - Future improvements suggested, such as integrating GPT-4 vision into the Assistants API, addressing pop-up issues, and implementing a cookie transferring mechanism. - Encouragement for contributions on GitHub for further enhancements. Made with HARPA AI

I am unable to get this code to work either. I get that same error as well about the fileID being none. 🤔

can you create Agency Swarm using Gemini pro api ?

You are genius

😍😍😍

I think it will be easier with Google Gemini.

❤

my best AI agent right framework right now, but it makes a lot of API calls which cost lost of money.

Legend ! .... "don't even try it" 🤣

What TOP use cases agency swarms can accomplish?

Just curious. Has anyone else got this codebase to work?

This shit works for qa automation?

Why is this tied to only openai, this is not scalable with other llms

Nice! Gleich mal einen Blick ins Repo werfen :3 Vielleicht versuch ich mich an einen der Tasks, die du bei 9:50 und 10:00. Schau ma mal ( •̀ ω •́ )✧

Looks great but You are really running a marathon with the tutorial. My issue is that your tutorial is not beginner friendly at all 😢

°∆ I believe we are meant to be like Jesus in our hearts and not in our flesh. But be careful of AI, for it knows only things of the flesh which are our fleshly desires and cannot comprehend things of the spirit such as true love and eternal joy that comes from obeying God's Word. Man is a spirit and has a soul but lives in a body which is flesh. When you go to bed it is the flesh that sleeps, but your spirit never sleeps and that is why you have dreams, unless you have died in peace physically. More so, true love that endures and last is a thing of the heart. When I say 'heart', I mean 'spirit'. But fake love, pretentious love, love with expectations, love for classic reasons, love for material reasons and love for selfish reasons those are things of the flesh. In the beginning God said let us make man in our own image, according to our likeness. Take note, God is Spirit and God is Love. As Love He is the source of it. We also know that God is Omnipotent, for He creates out of nothing and He has no beginning and has no end. That means, our love is but a shadow of God's Love. True love looks around to see who is in need of your help, your smile, your possessions, your money, your strength, your quality time. Love forgives and forgets. Love wants for others what it wants for itself. However, true love works in conjunction with other spiritual forces such as patience and faith - in the finished work of our Lord and Savior, Jesus Christ, rather than in what man has done such as science, technology and organizations which won't last forever. To avoid sin and error which leads to the death of your body and your spirit-soul in hell fire (second death), you must make God's Word the standard for your life, not AI. If not, God will let you face AI on your own (with your own strength) and it will cast the truth down to the ground, it will be the cause of so much destruction like never seen before, it will deceive many and take many captive in order to enslave them into worshipping it and abiding in lawlessness. We can only destroy ourselves but with God all things are possible. God knows us better because He is our Creater and He knows our beginning and our end. The prove text can be found in the book of John 5:31-44, 2 Thessalonians 2:1-12, Daniel 2, Daniel 7-9, Revelation 13-15, Matthew 24-25 and Luke 21. *HOW TO MAKE GOD'S WORD THE STANDARD FOR YOUR LIFE?* You must read your Bible slowly, attentively and repeatedly, having this in mind that Christianity is not a religion but a Love relationship. It is measured by the love you have for God and the love you have for your neighbor. Matthew 5:13 says, "You are the salt of the earth; but if the salt loses its flavor, how shall it be seasoned? It is then good for nothing but to be thrown out and trampled underfoot by men." Our spirits can only be purified while in the body (while on earth) but after death anything unpurified (unclean) cannot enter Heaven Gates. Blessed are the pure in heart, for they shall see God (Matthew 5:8). No one in his right mind can risk or even bare to put anything rotten into his body nor put the rotten thing closer to the those which are not rotten. Sin makes the heart unclean but you can ask God to forgive you, to save your soul, to cleanse you of your sin, to purify your heart by the blood of His Son, our Lord and Savior, Jesus Christ which He shed here on earth - "But He was wounded for our transgressions, He was bruised for our iniquities; the chastisement for our peace was upon Him, and by His stripes we are healed", Isaiah 53:5. Meditation in the Word of God is a visit to God because God is in His Word. We know God through His Word because the Word He speaks represent His heart's desires. Meditation is a thing of the heart, not a thing of the mind. Thinking is lower level while meditation is upper level. You think of your problems, your troubles but inorder to meditate, you must let go of your own will, your own desires, your own ways and let the Word you read prevail over thinking process by thinking of it more and more, until the Word gets into your blood and gains supremacy over you. That is when meditation comes - naturally without forcing yourself, turning the Word over and over in your heart. You can be having a conversation with someone while meditating in your heart - saying 'Thank you, Jesus...' over and over in your heart. But it is hard to meditate when you haven't let go of offence and past hurts. Your pain of the past, leave it for God, don't worry yourself, Jesus is alive, you can face tomorrow, He understands what you are passing through today. Begin to meditate on this prayer day and night (in all that you do), "Lord take more of me and give me more of you. Give me more of your holiness, faithfulness, obedience, self-control, purity, humility, love, goodness, kindness, joy, patience, forgiveness, wisdom, understanding, calmness, perseverance... Make me a channel of shinning light where there is darkness, a channel of pardon where there is injury, a channel of love where there is hatred, a channel of humility where there is pride..." The Word of God becomes a part of us by meditation, not by saying words but spirit prayer (prayer from the heart). When the Word becomes a part of you, it will by its very nature influence your conduct and behavior. Your bad habits, you will no longer have the urge to do them. You will think differently, dream differently, act differently and talk differently - if something does not qualify for meditation, it does not qualify for conversation. *THE BATTLE BETWEEN LIGHT AND DARKNESS (GOOD AND EVIL)* Heaven is God's throne and the dwelling place for God's angels and the saints. Hell was meant for the devil (satan) and the fallen angels. Those who torture the souls in hell are demons (unclean spirits). Man's spirit is a free moral agent. You can either yield yourself to God or to the devil because God has given us discretion. If one thinks he possesses only his own spirit, he is lying to himself and he is already in the dark. God is light while the devil is darkness. Light (Holy Spirit) and darkness (evil spirit) cannot stay together in a man's body. God is Love (Love is light) and where there is no love is hell, just as where there is no light is darkness. The one you yield yourself to, you will get his reward. The reward of righteousness to man's spirit is life (abundant life) and the reward of sin to man's spirit is death. Sin and satan are one and the same. Whatever sin can cause, satan also can cause. Sin is what gives the devil dominion or power over man's spirit. When God's Word becomes a part of you, sin power over you is broken, you become the righteousness of God through Christ Jesus. Where Jesus is, you are and when He went (to the Father), you went. In the book of John 8:42-47, Jesus said to them, “If God were your Father, you would love Me, for I proceeded forth and came from God; nor have I come of Myself, but He sent Me. Why do you not understand My speech? Because you are not able to listen to My word. You are of your father the devil, and the desires of your father you want to do. He was a murderer from the beginning, and does not stand in the truth, because there is no truth in him. When he speaks a lie, he speaks from his own resources, for he is a liar and the father of it. Which of you convicts Me of sin? And if I tell the truth, why do you not believe Me? He who is of God hears God’s words; therefore you do not hear, because you are not of God.” May God bless His Word in the midst of our hearts. Glory and honour be to God our Father, our Lord and Savior Jesus Christ and our Helper the Holy Spirit. Watch and pray!... Thank you for your time and may God bless you as you share this message with others.