Event ended

Langchain x Autonomous GPT Agents Hackathon Summary

Langchain x Autonomous GPT Agents Hackathon image

Hackathon Overview

Our AI hackathon brought together a diverse group of participants, who collaborated to develop a variety of impressive projects based on:

773

Participants

116

Teams

17

AI Applications

Winners and Finalists

medal

MarkU - Automatic Marketing

MarkU is an innovative automated content marketing solution that streamlines your marketing efforts using AI-driven technology. By leveraging the power of Langchain with OpenAI GPT-3.5, MarkU conducts in-depth market analysis, competitor assessments, and identifies unique selling points to create contextually relevant social media posts. Integrated with Serper for automatic Googling, MarkU offers unparalleled market research capabilities. MarkU revolutionizes your content marketing strategy, saving you time and resources while optimizing your brand's online presence. Experience the future of marketing automation with MarkU.

Trivialis

ChatGPTLangChainGenerative AgentsAuto-GPTGPT-4GPT-3
medal
replit
application badge

Organize your storage with AI

This project aims for professionals and students that might have mess in their files. They might not know where it is, and need a quick searcher. Martha is here to help! She will iterate and extract information of each document you might have, then based on a given description, she will compare each file and find the right for you! This tool was created using langchain agents and ChatGPT. For the future we are looking to: 1. Apply Martha for cloud servicies (such as Google drive, Icloud or Onedrive) 2. Let Martha organize your documents in a list of folders and sorting within common topics.

Proyect MARTHA

LangChainChatGPT
medal

GPT-Swarm

GPT-Swarm is a groundbreaking project that combines swarm intelligence and advanced language models to tackle complex tasks across diverse domains. Our innovative framework is robust, adaptive, and scalable, outperforming single models by leveraging the power of collective problem-solving and distributed decision-making. Not to mention the lightning-fast speed with which it performs the research. Our team has meticulously designed GPT-Swarm to be adaptive, responsive, and efficient, capitalizing on the collective intelligence of numerous GPT models working synergistically. By having these models collaborate, we can significantly enhance performance and deliver superior results compared to traditional methods. In one of our primary use cases, we have deployed GPT-Swarm to conduct comprehensive background checks on startups and idea spaces. This process involves evaluating their credibility, financial stability, and potential for growth, ensuring a well-rounded understanding of each venture's viability. Our innovative approach allows for a more in-depth analysis, equipping investors and stakeholders with invaluable insights for better decision-making. By submitting GPT-Swarm to this hackathon competition, we aim to showcase the immense potential of swarm intelligence in transforming the landscape of artificial intelligence and machine learning. Our project not only highlights the power of collaboration among GPT models but also sets a new benchmark for tackling complex tasks and challenges. Join us as we embark on this exciting journey towards a more intelligent and interconnected future.

AutoSwarm

medal

ETHOS

ETHOS - Evaluating Trustworthiness and Heuristic Objectives in Systems - is a groundbreaking project that addresses the critical issue of AI alignment. As AI continues to evolve and become increasingly sophisticated, it is becoming increasingly clear that alignment is one of the most significant challenges we face in developing this technology. Unaligned AI has the potential to cause catastrophic damage to society and humanity as a whole. ETHOS is an API that provides a solution to this problem. It is designed to evaluate the trustworthiness and heuristic objectives of AI systems, from language models to autonomous agents and chatbots. The API allows for the real-time adjustment of responses, ensuring that AI systems remain aligned with the goals of humanity. The need for AI alignment is becoming more urgent as AI systems become more prevalent in our daily lives. These systems are used in everything from social media algorithms to self-driving cars, and they have the potential to impact many different aspects of our lives. If these systems are not aligned with our values and goals, they could cause significant harm. One of the most significant threats posed by unaligned AI is the potential for these systems to become adversarial. Adversarial AI is a form of AI that is intentionally designed to cause harm. This could take the form of cyberattacks, data breaches, or even physical harm to individuals or infrastructure. Adversarial AI could also be used to manipulate public opinion, disrupt democratic processes, or sow discord and chaos. ETHOS provides a way to mitigate these risks by ensuring that AI systems are aligned with their intended purpose. By evaluating the trustworthiness of AI systems, ETHOS can detect when an AI system is deviating from its intended purpose and adjust its responses in real-time. This can prevent AI systems from becoming adversarial and ensure that they are working in the best interests of society.

CogArk

BabyAGIOpenAIGPT-4GPT-3

Speakers, Mentors, and Organizers

Yury Brankouski profile picture
mentor

Yury Brankouski

CPO

    Dimitrije Pesic profile picture
    mentor

    Dimitrije Pesic

    Student

    Omar Sesa profile picture
    mentor

    Omar Sesa

    Assistant Lecturer in AI, ML and embedded systems field

    Theodoros Ampas profile picture
    mentor

    Theodoros Ampas

    Co-Founder of Content-Hive

    Muhammad Zubair Zafar profile picture
    mentor

    Muhammad Zubair Zafar

    Software Engineer

    Skander Karoui profile picture
    mentor

    Skander Karoui

    Data Science and AI enthusiast || ICT Engineer

    Liza Marchuk profile picture
    organizer

    Liza Marchuk

      Anastasiia Strakhova profile picture
      organizer

      Anastasiia Strakhova

      Event Specialist at NewNative

        Jakub Zakrzewski profile picture
        organizer

        Jakub Zakrzewski

        Product Manager

        Fabian Stehle profile picture
        organizer

        Fabian Stehle

        Dev at NN

        Mathias Asberg profile picture
        organizer

        Mathias Asberg

        founder

          Olesia Zinchenko profile picture
          organizer

          Olesia Zinchenko

          Event Manager & Mentor at lablab.ai

          Pawel Czech profile picture
          organizer

          Pawel Czech

          Co-founder/Partner

            Simon Olson profile picture
            organizer

            Simon Olson

            Founder

            Harrison Chase profile picture
            mentor

            Harrison Chase

            Machine Learning Engineer

              Ankur Singh profile picture
              speaker

              Ankur Singh

              Founder

                Mihir Chouhan profile picture
                mentor

                Mihir Chouhan

                Project Manager

                  Fabian Stehle profile picture
                  mentor

                  Fabian Stehle

                  Dev at NN

                  Marek Mardosewicz profile picture
                  mentor

                  Marek Mardosewicz

                  Maksym Wolff profile picture
                  mentor

                  Maksym Wolff

                  Event Spec.

                    Nate Rundberg profile picture
                    mentor

                    Nate Rundberg

                    Slingshot Project Coordinator

                      Rita Svitlychenko profile picture
                      mentor

                      Rita Svitlychenko

                      HR

                        Simon Olson profile picture
                        mentor

                        Simon Olson

                        Founder

                        Daniel Duccik profile picture
                        mentor

                        Daniel Duccik

                        Marketing&Visual

                        Prizes

                        Winner

                        • SWAG from lablab.ai

                        Best Projects

                        • SWAG from lablab.ai

                        This event has now ended, but you can still register for upcoming events on lablab.ai. We look forward to seeing you at the next one!

                        Checkout Upcoming Events →

                        Submitted Concepts, Prototypes and Pitches

                        Submissions from the teams participating in the Langchain x Autonomous GPT Agents Hackathon event and making it to the end 👊

                        Help to spread the word and share these amazing projects!

                        medal
                        replit
                        application badge

                        Organize your storage with AI

                        This project aims for professionals and students that might have mess in their files. They might not know where it is, and need a quick searcher. Martha is here to help! She will iterate and extract information of each document you might have, then based on a given description, she will compare each file and find the right for you! This tool was created using langchain agents and ChatGPT. For the future we are looking to: 1. Apply Martha for cloud servicies (such as Google drive, Icloud or Onedrive) 2. Let Martha organize your documents in a list of folders and sorting within common topics.

                        Proyect MARTHA

                        LangChainChatGPT
                        Streamlit
                        application badge

                        Study - Ask questions and mor

                        In this app the user will be able to upload any pdf and will able to retrieve information by asking questions in chat format. The answers will be available in audio format as well which will increase the accessibility of the application. In case the user wants to search more about a particular topic from pdf, beyond the scope of the literature present in PDF, he/she will be able to do that as well in a separate page called Research. Where answers will be retrieved from internet through Google Search and Wikipedia. There is a separate page to takes notes during these learning process where the text persists even if the user goes to a different page and at the end user will be able to download it. Last but not least, There is a separate page where User will be able to ask questions to chatGPT.

                        Zion

                        OpenAILangChainChatGPT
                        Streamlit
                        application badge

                        Carrer-AIdvisor

                        Have you ever wondered how your CV is received by HR consultants and recruiters? How much you actually fit the role of the job posting and what you can improve on? With career-aidvisor you can peek behind the scenes of the recruitment process. career-aidvisor creates an hypothetical scenario in which an HR consultant asks an IT recruiter for an evaluation of your resume/cv. Powered by Lancghain Chat model agents, they will talk about weaknesses, strengths, points of improvement, etc. Which you can you use to improve your profile and focus your effort in studying new technologies or developing the necessary skills to land your next job.

                        Laia team

                        LangChainOpenAIGenerative Agents
                        medal

                        GPT-Swarm

                        GPT-Swarm is a groundbreaking project that combines swarm intelligence and advanced language models to tackle complex tasks across diverse domains. Our innovative framework is robust, adaptive, and scalable, outperforming single models by leveraging the power of collective problem-solving and distributed decision-making. Not to mention the lightning-fast speed with which it performs the research. Our team has meticulously designed GPT-Swarm to be adaptive, responsive, and efficient, capitalizing on the collective intelligence of numerous GPT models working synergistically. By having these models collaborate, we can significantly enhance performance and deliver superior results compared to traditional methods. In one of our primary use cases, we have deployed GPT-Swarm to conduct comprehensive background checks on startups and idea spaces. This process involves evaluating their credibility, financial stability, and potential for growth, ensuring a well-rounded understanding of each venture's viability. Our innovative approach allows for a more in-depth analysis, equipping investors and stakeholders with invaluable insights for better decision-making. By submitting GPT-Swarm to this hackathon competition, we aim to showcase the immense potential of swarm intelligence in transforming the landscape of artificial intelligence and machine learning. Our project not only highlights the power of collaboration among GPT models but also sets a new benchmark for tackling complex tasks and challenges. Join us as we embark on this exciting journey towards a more intelligent and interconnected future.

                        AutoSwarm

                        Streamlit
                        application badge

                        WordForge

                        The goal is to develop AI Tools to help in the creation of text content for e-commerce shops. The idea is a text generator specialized in product descriptions and website texts. The user gives a few inputs in a fast, simple and interactive way and then LangChain creates the prompts and ChatGPT the desired text. Advantages for users : Generate very accurate texts, perfectly tailored to your brand, communication strategy and tone It enables coherent and consistent communication throughout the website, as you will always use the same parameters for a specific brand. It will help e-commerce owners leverage the full potential of the web shop and translate it into other languages.

                        WordForge

                        LangChainOpenAI
                        medal

                        ETHOS

                        ETHOS - Evaluating Trustworthiness and Heuristic Objectives in Systems - is a groundbreaking project that addresses the critical issue of AI alignment. As AI continues to evolve and become increasingly sophisticated, it is becoming increasingly clear that alignment is one of the most significant challenges we face in developing this technology. Unaligned AI has the potential to cause catastrophic damage to society and humanity as a whole. ETHOS is an API that provides a solution to this problem. It is designed to evaluate the trustworthiness and heuristic objectives of AI systems, from language models to autonomous agents and chatbots. The API allows for the real-time adjustment of responses, ensuring that AI systems remain aligned with the goals of humanity. The need for AI alignment is becoming more urgent as AI systems become more prevalent in our daily lives. These systems are used in everything from social media algorithms to self-driving cars, and they have the potential to impact many different aspects of our lives. If these systems are not aligned with our values and goals, they could cause significant harm. One of the most significant threats posed by unaligned AI is the potential for these systems to become adversarial. Adversarial AI is a form of AI that is intentionally designed to cause harm. This could take the form of cyberattacks, data breaches, or even physical harm to individuals or infrastructure. Adversarial AI could also be used to manipulate public opinion, disrupt democratic processes, or sow discord and chaos. ETHOS provides a way to mitigate these risks by ensuring that AI systems are aligned with their intended purpose. By evaluating the trustworthiness of AI systems, ETHOS can detect when an AI system is deviating from its intended purpose and adjust its responses in real-time. This can prevent AI systems from becoming adversarial and ensure that they are working in the best interests of society.

                        CogArk

                        BabyAGIOpenAIGPT-4GPT-3
                        medal

                        MarkU - Automatic Marketing

                        MarkU is an innovative automated content marketing solution that streamlines your marketing efforts using AI-driven technology. By leveraging the power of Langchain with OpenAI GPT-3.5, MarkU conducts in-depth market analysis, competitor assessments, and identifies unique selling points to create contextually relevant social media posts. Integrated with Serper for automatic Googling, MarkU offers unparalleled market research capabilities. MarkU revolutionizes your content marketing strategy, saving you time and resources while optimizing your brand's online presence. Experience the future of marketing automation with MarkU.

                        Trivialis

                        ChatGPTLangChainGenerative AgentsAuto-GPTGPT-4GPT-3

                        RedTeamAGPT

                        RedAGPT is an innovative and comprehensive solution designed to test network and other vulnerabilities for homes and offices. It uses cutting-edge technologies such as AutoGPT and Langchain to offer a highly efficient and effective security testing experience. The tool kit is designed with a focus on prompt engineering and seamless integration into security-focused Linux environments. This ensures that security professionals can easily use the tool kit to test for vulnerabilities in their networks and systems. The core technology used in the tool kit is AI, specifically AutoGPT using GPT-3 via the Langchain library. The AI runs a series of tests to detect vulnerabilities in the network and systems to then analyze the results of these tests and generate a comprehensive security report. This report details the vulnerabilities detected, their severity level, and recommendations on how to fix them. Overall, the tool kit for security professionals is a game-changer in the field of security testing. Its use of AI and its ability to generate comprehensive reports makes it an essential tool for security professionals looking to keep their networks and systems secure.

                        RedTeamAGPT

                        LangChainRedisReinforcement LearningAuto-GPTGPT-3
                        Streamlit
                        application badge

                        Weekend wonders

                        We replicated our friend Sophie. A super mum and super planner. All her weekends are packed with fun and creative family activities. How does she manage to pull that off? Where does she find the time and creativity? Enter Weekend Wonders. A simple weekend planner that helps discover delightful family weekend activities with the push of a button. As four geeky dads, we chained together large language models, weather API's and AI agents, to automate this discovery process. - Get tailored activities, based on your family profile and location. - Factor in the weather to plan the right activities and outfit. - Inject extra creativity in your typical activities. - Get real-time accurate info about open hours and prices. We'd also like to take it a step further, and get an AI agent to scour the web to automatically pull in relevant event info.

                        The Pizza Waffles

                        OpenAILangChain

                        CotChat

                        CotChat is a community chatbot that determines its conversational behaviour through REACT method based on ChatGPT and LangChain. Unlike ordinary chatbots, CotChat uses the approach proposed by React. When receiving messages, it automatically infers the appropriate action through observation-interest evaluation-reflection-action. We have defined three types of behaviours: Direct reply: Reply directly to the current message, Relate reply: Related to memory vectors and Silent: Feel this message is irrelevant and feel uninterested. In this example, we collaborated with artist Nick to create a chatbot based on his character LuckyCot. This character is a cat named Modem Cot that mutated from a network mediator modem and has a network cable tail. It is interested in blockchain-related content. [图片] [图片] The thinking process (steps) of this bot can be summarized as follows: 1. Observe: Understand what is being discussed in the current conversation. 2. Evaluate: Rate the interest and relevance of the message on a scale of 1 to 10, where 1 is not interested or related, and 10 is extremely interested and related. This is a reference value for agent's decision. 3. Reflect: Identify any associated emotions, relevant memories or users, and determine if the bot is interested or related (evaluation score greater than 7). 4. Action: Choose one of the predefined actions (Direct reply, Silent, or Relate reply) based on the observation, evaluation, and reflection. In summary, we have applied the Observe-reasoning-action approach proposed in React to community chatbots. Currently, this application is displayed through WeChat. We hope that in the future, Autonomous Agents can truly become members of human society.

                        hyborg-cat

                        Period Fact Checker

                        Aiming to barricade misinformation spread in the internet, we built Period! Fact checker, a universal fact checker for anything on the web. Period! Fact Checker is your personal assistant on a chrome extension powered by LangChain Autonomous agent that can perform a fact check on any body of text in the web. Currently optimized for articles (news, entertainment, gossip) it can perform fact check based on cross checking to other sites and would cite the references used. It would also produce a final score ranging from 1 to 100 on how accurate the body of text is. With a simple click, just ask period to do the heavy work for you, and you can always stay out of misinformation. Period!

                        One Three Three

                        LangChainGenerative AgentsOpenAIGPT-3

                        Personal CIA

                        Personal CIA is a web application that generates customized market results based on your query. By allowing you to filter your target and choose a desired search timeframe, it provides more precise outcomes. To enhance user prompts, we used ChatGPT, which we then fed to AutoGPT for autonomous research. Users can track AutoGPT's progress and view results when the research is complete. If the search is successful, the dashboard displays the reach; otherwise, no results are shown. We chose this project to reduce the time and cost of conducting market research and provide more organized and well-researched results for better market understanding

                        Meow Lab

                        ChatGPTAuto-GPT

                        Auto-Wiki

                        Introducing Auto-Wiki, an AI-powered tool designed to significantly improve the way researchers access and stay informed about the latest research papers. At the core of this solution is the seamless curation and summarization of research papers, which allows scholars to stay in the loop and well-informed without spending endless hours searching and reading. Auto-Wiki's primary goal is to provide a high-level understanding of new research papers' key points and findings, enabling researchers to focus on the most relevant information and make well-informed decisions. By automatically adding generated summaries to a wiki, Auto-Wiki fosters collaboration and ensures that the research community stays interconnected and updated. Ideal for a fast-paced academic environment, Auto-Wiki revolutionizes the way researchers stay informed, paving the way for groundbreaking discoveries and insights. This innovative solution not only saves time and effort but also encourages the development of new ideas and connections between various research fields. Experience the future of research with Auto-Wiki.

                        Auto-Wiki

                        LangChainOpenAI
                        Streamlit
                        application badge

                        Consulting Trainer

                        Consulting Trainer is a platform that, through LangChain and CAMEL, allows you to train your workers, mainly consultants, and auditors, in the interview processes that they have to do with clients when raising requirements. To do this, the user must specify the objective of the interview (project being evaluated), define the role of the person interviewed (stakeholder, client, etc.), and the role that this user will play (consultant, developer, etc.). Next, Consulting Trainer will begin to display a dialog about how the interview process should be so that the user has the ability to understand this process and learn for its subsequent execution. This project aims to make it easier for companies to train their junior professionals, who sometimes, due to conventional teaching methods, are not fully productive, and can now learn through a simulation, closer to reality.

                        AmalIA

                        LangChainCAMEL
                        Streamlit
                        application badge

                        QuizMeGPT

                        Introducing the ultimate study tool that enables students to study productively and independently: our innovative study tool that helps students analyze textbook material, quiz themselves, and receive feedback on their answers. Our tool is designed to help students achieve their full potential by providing them with an effective learning experience that is tailored to their individual needs. With our study tool, students can import their textbook and the tool will automatically split the material into smaller chunks. The tool uses advanced AI technologies to generate questions based on the textbook material and quiz the student on the material. The student can then receive feedback on their answers, with the tool providing encouraging feedback on whether their answer is correct and how they can improve.

                        QuizMeGPT

                        LangChainOpenAI

                        MintBuddy

                        Are you tired of feeling left out of the cryptocurrency world because of the confusing technology and jargon? Enter MintBuddy - the revolutionary blockchain chatbot that simplifies the process of minting your own NFTs without needing any prior knowledge of blockchain technology. With our AI-driven chatbot, you can easily send money, buy crypto, and mint NFTs with a simple text message. MintBuddy leverages cutting-edge technologies, including Voiceflow, Verbwire API, and OpenAI, to create a user-friendly and accessible platform that makes blockchain technology and cryptocurrencies available to everyone, regardless of their technical knowledge or experience. Our platform is so easy to use that even your grandma can start using it to take control of her finances. Our mission is to solve the problem statement of how complex the world of cryptocurrency can be. We believe that BitBuddy is the solution that will drive mass adoption of cryptocurrencies, empowering people to take control of their finances. By simplifying the process of interacting with these complex systems, we're making it possible for everyone to participate in the cryptocurrency market. With MintBuddy, you can buy and sell crypto directly through the chatbot, eliminating the need for you to navigate complex trading platforms. We're constantly improving the platform, adding more features like tutorials, gamification elements, and more information on cryptocurrencies and NFTs, making the experience even more engaging. Our goal is to make MintBuddy the go-to platform for anyone who wants to interact with cryptocurrency and blockchain technology. We believe that by continuing to improve the platform and making it even more user-friendly, we can help to demystify the complexities of blockchain technology and empower more people to take control of their finances.

                        CryptoChats

                        AI Agent for Human Resource

                        HR-GPT is a tool that small businesses can use to improve their HR procedures and support their remote workers. The AI agent provides information related to HR policies (onboarding information, employee handbook, IT services, etc..). It is designed to help businesses stay compliant with HR standards without the need for a substantial HR department or expertise. One of the key benefits of the app is that it provides remote workers with quick access to important information. This includes updates on company policies and procedures, time-off requests, payroll information, and employee benefits. By using the app, remote workers can stay connected with their colleagues and the company, even if they are not physically present in the workplace. The app is easy to use and can be customized to meet the specific needs of each business. Admins can quickly load new documents into the agent through Slack's slash command, directly in Slack.

                        Toasted

                        LangChainOpenAI