npm install exa-js

import Exa from 'exa-js';

const exa = new Exa(process.env.EXA_API_KEY);

const result = await exa.searchAndContents(
  "hottest AI startups",
  {
    type: "neural",
    useAutoprompt: true,
    numResults: 10,
    text: true,
  }
);
console.log(result);

{
  autopromptString: 'A top AI startup to watch is:',
  results: [
    {
      score: 0.20460350811481476,
      title: 'OpenAI',
      id: 'https://openai.com/',
      url: 'https://openai.com/',
      publishedDate: '2021-06-18',
      author: 'OpenAI',
      text: 'Creating safe AGI that benefits all of humanity Pioneering research on the path to AGI Transforming work and creativity with AI Join us in shaping the future of technology Safety & responsibility Our work to create safe and beneficial AI requires a deep understanding of the potential risks and benefits, as well as careful consideration of the impact. Learn about safety Research We research generative models and how to align them with human values. Learn about our research GPT-4 March 14, 2023 Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk January 11, 2023 Point-E: A system for generating 3D point clouds from complex prompts December 16, 2022 Introducing Whisper September 21, 2022 Products Our API platform offers our latest models and guides for safety best practices. Explore our products New and improved embedding model December 15, 2022 DALL·E now available without waitlist September 28, 2022 New and improved content moderation tooling August 10, 2022 New GPT-3 capabilities: Edit & insert March 15, 2022 Careers at OpenAI Developing safe and beneficial AI requires people from a wide range of disciplines and backgrounds. View careers I encourage my team to keep learning. Ideas in different topics or fields can often inspire new ideas and broaden the potential solution space. Lilian WengApplied AI at OpenAI'
    },
    {
      score: 0.18225537240505219,
      title: 'Build Trust',
      id: 'https://thotai.com/',
      url: 'https://thotai.com/',
      publishedDate: '2023-01-01',
      author: null,
      text: 'This website uses cookies to enhance your experience. By continuing to browse, you agree to our use of cookies.\n' +
        '\n' +
        'Discover\n' +
        ' Design and architect the path to safe artificial general intelligence\n' +
        '\n' +
        'Build Trust\n' +
        ' ThotAI is a global organization with a strong research laboratory based in Seattle, Washington. Our mission is to ensure that artificial general intelligence benefits all of humanity. The ThotAI Charter describes the principles that guide us as we execute on our mission.\n' +
        ' ThotAI’s mission is to ensure that artificial general intelligence (AGI)—by which we mean highly autonomous systems that outperform humans at most economically valuable work—benefits all of humanity. We will attempt to directly build safe and beneficial AGI, but will also consider our mission fulfilled if our work aids others to achieve this outcome.\n' +
        '\n' +
        'Our principles\n' +
        '\n' +
        'Broadly Distributed Benefits\n' +
        ' We commit to use any influence we obtain over AGI’s deployment to ensure it is used for the benefit of all, and to avoid enabling uses of AI or AGI that harm humanity or unduly concentrate power.\n' +
        '\n' +
        'Our primary fiduciary duty is to humanity. We anticipate needing to marshal substantial resources to fulfill our mission, but will always diligently act to minimize conflicts of interest among our employees and stakeholders that could compromise broad benefit.\n' +
        '\n' +
        'Long-Term Safety\n' +
        ' We are committed to doing the research required to make AGI safe, and to driving the broad adoption of such research across the AI community.\n' +
        '\n' +
        'We are concerned about late-stage AGI development becoming a competitive race without time for adequate safety precautions. Therefore, if a value-aligned, safety-conscious project comes close to building AGI before we do, we commit to stop competing with and start assisting this project. We will work out specifics in case-by-case agreements\n' +
        '\n' +
        'Technical Leadership\n' +
        ' To be effective at addressing AGI’s impact on society, OpenAI must be on the cutting edge of AI capabilities—policy and safety advocacy alone would be insufficient.\n' +
        '\n' +
        'We believe that AI will have broad societal impact before AGI, and we’ll strive to lead in those areas that are directly aligned with our mission and expertise.\n' +
        '\n' +
        'Cooperative Orientation\n' +
        ' We will actively cooperate with other research and policy institutions; we seek to create a global community working together to address AGI’s global challenges.\n' +
        '\n' +
        'We are committed to providing public goods that help society navigate the path to AGI. Today this includes publishing most of our AI research, but we expect that safety and security concerns will reduce our traditional publishing in the future, while increasing the importance of sharing safety, policy, and standards research.\n' +
        '\n' +
        'Your browser does not support HTML5 video.'
    },
    {
      score: 0.1814948320388794,
      title: 'Home | Tenyx, Inc.',
      id: 'https://www.tenyx.com/',
      url: 'https://www.tenyx.com/',
      publishedDate: '2019-09-10',
      author: null,
      text: "TENYX IS DEVELOPING THE NEXT-GENERATION OF INTELLIGENT MACHINES BASED ON PROPRIETARY NEUROSCIENCE-INSPIRED AI TECHNOLOGY Tenyx in the News Robust voice-based conversational agents We are tackling some of the core challenges facing existing AI solutions, including the ability to learn continually from new information in real-time and the need to dramatically reduce model training times. Using proprietary neuroscience-inspired AI technology, our team is building the next generation of voice-based conversational agents: intelligent, interactive, and with the common-sense reasoning lacking today. Addressing some of the key challenges of current AI technology We're Hiring ...​\n" +
        '​\n' +
        'We are a team of researchers and engineers led by an experienced leadership team with a track record of building successful AI companies from the ground up. We are looking for talented individuals with strong analytical capabilities, machine learning experience and solid coding skills, who are passionate about delivering the next-generation of AI technology and building highly impactful products. If that’s you please email us at: [email protected]. Research Scientist (Palo Alto, CA – multiple positions) \n' +
        '​\n' +
        'Conduct applied research and product development with a focus on ML and AI technologies using mathematical and analytical theories, techniques and tools.\n' +
        '​\n' +
        'Specific duties include:\n' +
        ' Developing mathematical models pertaining to deep learning models that mitigate catastrophic forgetting via non-gradient-based optimization.\n' +
        ' Developing hierarchical models of representation that capture regularities in observations and map those to a decision space whereby each layer of the hierarchy corresponds to a different spatiotemporal scale.\n' +
        ' Employing mathematical techniques derived from stochastic processes, linear algebra, estimation theory, and information theory.\n' +
        ' Developing and evaluating applied research code, including devising simulation and testing environments to illustrate the capabilities of new machine learning algorithms and architectures in various problem domains, including those involving visual and auditory input streams.\n' +
        '\n' +
        'REQ: MS or foreign equivalent in Computer Science, Electrical Engineering, Applied Mathematics, or closely related field. Must have knowledge of linear algebra, calculus, and stochastic processes; machine learning theory and practice, including supervised and unsupervised learning algorithms, reinforcement learning, and sequential decision-making under uncertainty; and mathematical modeling techniques and data science, including classification and regression methods, regularization techniques, and ensemble learning methodologies. Must also have 2 years of experience (either in graduate school or post-graduate studies) with Python and PyTorch. Experience can be concurrent. Send cover letter with resume to: I. Arel at Tenyx, 455B Portage Avenue, Palo Alto, CA 94306 or via email: [email protected]. No calls.\n' +
        '​ VP of Research and Development (Palo Alto, CA) \n' +
        '​\n' +
        'Lead the company’s research and development activities, including managing teams of engineers and researchers working on different aspects of the company’s software technology and products. Will have oversight of the company’s technical roadmap and will be responsible for delivering software solutions that utilize the company’s proprietary neuroscience-inspired machine learning technologies.\n' +
        '\n' +
        'Specific duties include:\n' +
        ' Developing algorithms, software architectures, and code that implement a novel machine learning framework developed by the company.\n' +
        ' Contributing to the mathematical modeling of these algorithms and to the Python and PyTorch implementations of the code.\n' +
        ' Supporting the design of evaluation environments used to determine the performance of the systems developed.\n' +
        ' Contributing to the successful deployment of the company’s solutions by supporting customers with technical documentation and questions.\n' +
        '\n' +
        'REQ: PhD or foreign equivalent in Computer Science, Computational/Applied Mathematics, Electrical Engineering, or Computer Engineering + 3 years of post- graduate software engineering experience, particularly with products involving machine learning technologies, including TTS and ASR systems and language identification; large language models and ontological development; and DRL/theory of deep learning. Required experience must include advanced linear algebra, optimization/approximation theory, and statistics; software system architecture (design principles, code & code quality principles, software deployment, and continuous integration); Advanced Python, Jupyter Notebooks, and Bash; and deep learning frameworks (SKLearn, MxNet, TensorFlow and PyTorch). Must also have 2 years of experience as an Engineering Manager or similar, overseeing R&D activities and leading software development teams of at least 20 PhD-level applied researchers in the AI space, and including experience with program management, delivering end-to-end, multi-month/year, cross-functional deep technical programs. Experience can be concurrent. Send cover letter w/resume to: I. Arel at Tenyx, 455B Portage Avenue, Palo Alto, CA 94036 or via email: [email protected]. No calls.\n' +
        "​ Who we are First and foremost, we are a team of researchers and engineers passionate about building truly intelligent machines. Our conviction is that intelligent machines will pave the way to addressing some of humanity's greatest challenges; from drug discovery and education to climate change. We are pursuing a pragmatic roadmap delivering significant improvements to existing AI capabilities which will endow machines with the ability to solve problems that are currently considered beyond the scope of AI technologies. \n" +
        '​\n' +
        'Tenyx is led by the founding team behind Apprente, which developed the world’s first voice-based AI solutions to automate the order-taking process at drive-thru restaurants. Apprente was acquired by McDonald’s Corporation and subsequently by IBM. The seasoned leadership at Tenyx includes Dr. Itamar Arel, a former professor of AI and CEO at Apprente, and Prof. Ron Chrisley, an established AI researcher and head of the Cognitive Science program at Sussex University. Among its advisors are renowned AI and neuroscience researchers, including professors Noah Goodman, David Eagleman and Shaul Druckmann all from Stanford University. Our focus Our initial product focus is on utilizing our groundbreaking research outcomes to build the next-generation of intelligent voice-based agents using our proprietary neuroscience-inspired AI technology. Leveraging our novel technological capabilities, Tenyx will deliver platforms that allow customers across multiple industries to rapidly deploy automated solutions that will dramatically reduce operating expenses while vastly improving both service levels and the overall customer experience. © 2022 by Tenyx, Inc.'
    },
    {
      score: 0.18110264837741852,
      title: 'AI21 Labs',
      id: 'https://www.ai21.com/',
      url: 'https://www.ai21.com/',
      publishedDate: '2000-01-01',
      author: null,
      text: "When Machines Become Thought Partners AI has a way to go before it matches human intelligence.We aim to get it a little bit closer. NLP is the NextAI Frontier We are at the start of a revolution in Natural Language Processing (NLP), or the ability of machines to understand and generate natural text. Itâ\x80\x99s no coincidence that language is a unique human ability, so making significant progress in NLP calls for considerable scientific and engineering innovations. At AI21 we aim to lead this revolution. And if we succeed, we'll have turned machines into the ultimate thought partners. We believe both writing and reading can be radically transformed by making them AI-first experiences. Machines should work alongside humans and empower them to be better versions of their writing and reading selves. Your thoughts in words AI21's premier product is a writing companion tool that helps you rephrase your writing to say exactly what you mean. Start Writing A revolutionaryreading experience Wordtune Read is an AI reader that summarizes long documents so you can understand more, faster. Start Reading Build scalable & efficient applications powered by AI21's state of the art language models that can process any language comprehension or generation task. No NLP expertise needed. Generate and Analyze Text With Easy-To-Use Large Language Model APIs AI21 Studio offers a new way to launch NLP-based applications, with an array of Large Language Model APIs, and with the ability to easily customize those models to suit the needs of your application. Build scalable & efficient applications powered by AI21's state of the art language models that can process any language comprehension or generation task. OurTechnology We believe that pattern recognition at scale - of the sort offered by current deep language models - is necessary but not sufficient to achieve our goals. Weâ\x80\x99re building enriched models that understand context and semantics at unprecedented levels. Research & more Dive into our demos, watch talks from our leadership, and read more about our advancements in natural language processing and machine learning. Read more"
    },
    {
      score: 0.18022897839546204,
      title: 'PlayAI',
      id: 'https://play.ai/',
      url: 'https://play.ai/',
      publishedDate: '2021-01-01',
      author: null,
      text: '* For Business\n' +
        ' * For Developers\n' +
        ' * Blog\n' +
        ' * About us\n' +
        ' Log inSign up\n' +
        '\n' +
        'The Voice Interface\n' +
        '\n' +
        'In conversation with\n' +
        ' Tap to talk to\n' +
        ' Click to talk to\n' +
        ' Play.ai\n' +
        ' Shuffle\n' +
        ' Share\n' +
        ' OR\n' +
        ' Create an Agent for free Discover use cases for Business\n' +
        ' Shuffle\n' +
        ' Share Create\n' +
        ' listening ...\n' +
        ' End Conversation'
    },
    {
      score: 0.17955060303211212,
      title: 'Cognition',
      id: 'https://www.cognition-labs.com/',
      url: 'https://www.cognition-labs.com/',
      author: null,
      text: "Makers of Devin, the first AI software engineer. Learn more here. We are an applied AI lab focused on reasoning, and code is just the beginning.‍To hire Devin for engineering work, please join the waitlist. We're a small team based in New York and the San Francisco Bay Area. Come work with us."
    },
    {
      score: 0.17942191660404205,
      title: 'Home',
      id: 'https://www.basis.ai/',
      url: 'https://www.basis.ai/',
      author: null,
      text: 'Creating a new kind of AI research organization.\n' +
        ' Introducing Basis ↗︎\n' +
        '\n' +
        "Advancing society's ability to solve hard problems.\n" +
        ' Learn more ↗︎\n' +
        '\n' +
        'Building a universal reasoning engine.\n' +
        ' Learn more ↗︎'
    },
    {
      score: 0.17900557816028595,
      title: 'Liquid AI: A New Generation of Foundation Models from First Principles',
      id: 'https://www.liquid.ai/',
      url: 'https://www.liquid.ai/',
      publishedDate: '2023-01-01',
      author: null,
      text: 'Seed Round Announcement We raised $37.6M in seed capital in November 2023. Liquid AI is excited to unveil the company to the world and announce that we raised $37.6M in seed capital, led by OSS Capital and PagsGroup (Steve Pagliuca, Chairman & CEO of PagsGroup). Spun out of MIT CSAIL, four founders - Ramin Hasani, Mathias Lechner, Alexander Amini, and Daniela Rus, started Liquid AI with the mission of building state-of-the-art, general-purpose AI systems that are capable, efficient, highly aligned, and trustworthy. Connect with us if you are a mathematician, physicist, neuroscientist, computer scientist, or engineer with the ambition to build truly intelligent systems for humanity. Get involved Liquid AI, Inc., 245 First St., 18th Floor, Cambridge, MA 02142 © , Liquid AI, Inc. All Rights Reserved.'
    },
    {
      score: 0.17744910717010498,
      title: 'GoodAI | Develop safe general artificial intelligence – as fast as possible – to help humanity and understand the universe.',
      id: 'https://www.goodai.com/',
      url: 'https://www.goodai.com/',
      publishedDate: '2023-01-16',
      author: null,
      text: 'Badger Architecture\n' +
        ' Badger Architecture is the culmination of five years of work at GoodAI. We developed an understanding that what we want is an agent that can quickly adapt to novel tasks.\n' +
        ' Explore\n' +
        '\n' +
        'Badger Seminars\n' +
        ' We run the series of Badger Seminars to bring together world-renowned experts in order to advance the field of life-long learning, meta-learning, multi-agent learning and other directions that we believe are relevant for building generally intelligent agents. \n' +
        ' Explore\n' +
        '\n' +
        'GoodAI Research Roadmap 2021/2022\n' +
        ' In 2021/22 GoodAI will focus on four core research areas: learning to learn, lifelong (gradual) learning, open-endedness, and generalization/extrapolation of meta-learned algorithms.\n' +
        ' Explore\n' +
        '\n' +
        'GoodAI Grants \n' +
        ' GoodAI is continuously awarding grants to research projects that push the boundaries of artificial intelligence.\n' +
        '\n' +
        'Explore\n' +
        '\n' +
        'Forbes Interview with Marek Rosa\n' +
        '\n' +
        'Why is stopping the development of the OpenAI platform foolish, and why is it unlikely that artificial intelligence will kill us all?\n' +
        ' Read more\n' +
        '\n' +
        'Review of 2022 & Plans for 2023\n' +
        '\n' +
        "Annual review on progress and what's in store for the upcoming year.\n" +
        ' Read more\n' +
        '\n' +
        'Research Diaries: Looking for the Emergence of Complex Behavior through Low-level rules and Memetics\n' +
        '\n' +
        "Investigating the underlying mechanisms of memetics and collective intelligence through FlatWorld's 2D environment.\n" +
        ' Read more\n' +
        '\n' +
        'Join GoodAI\n' +
        ' Are you keen on making a meaningful impact? Interested in joining the GoodAI team?\n' +
        '\n' +
        'View open positions'
    },
    {
      score: 0.17717614769935608,
      title: 'Adept: Useful General Intelligence',
      id: 'https://www.adept.ai/',
      url: 'https://www.adept.ai/',
      publishedDate: '2000-01-01',
      author: null,
      text: 'A new way to use computers\n' +
        '\n' +
        'We’re building a machine learning model that can interact with everything on your computer.\n' +
        '\n' +
        'Join the waitlist\n' +
        '\n' +
        'Our vision\n' +
        '\n' +
        'An AI teammate for everyone. \n' +
        ' Adept is building an entirely new way to get things done. It takes your goals, in plain language, and turns them into actions on the software you use every day.\n' +
        '\n' +
        'Collaborate and create\n' +
        '\n' +
        'Your hands on the wheel. \n' +
        " We believe that AI systems should be built with users at the center — where machines work together with people in the driver's seat: discovering new solutions, enabling more informed decisions, and giving us more time for the work we love.\n" +
        '\n' +
        'What they’re saying…\n' +
        '\n' +
        'We are hiring'
    }
  ],
  origQuery: 'A top AI startup to watch is:',
  requestId: '26f30c5ab664c2faf3be3cc608b4509a'
}