We're beyond excited to introduce StarSearch to you all. Our newest feature at OpenSauced! In 2022, I worked at GitHub and consistently got feedback from open-source maintainers that they’d love more insights. This is also true for builders who depend on open source to ship and iterate quickly. Founders are choosing open source, but few know who to connect with for expertise. 🌟 Why StarSearch? In the 90s, I watched a show on television at my grandma's house called StarSearch. This same show discovered Beyonce, Ryan Gosling, and Justin Timberlake before they were stars. This new and complementary feature is live in our OpenSauced product today, and we have indexed millions of GitHub events and are excited to get your feedback on the approach. 🍕 Track impactful developers from open source projects 🍕 Discover new projects in open source 🍕 Identify your next core contributors Using StarSearch, you can find up-and-coming contributors through trends in public open-source data, which can set you apart from the rest when building. We love open source and want more folks connected to the who's who in this space. StarSearch is our first exploration of adding semantic search to fetch relevant context on the projects used, built, and depended on. 👀 Try it out and run the following test prompts https://oss.fyi/starsearch Who are some Tailwind experts who also have an interest in Rust? Who are the prevalent contributors in the Typescript ecosystem? What pull requests has charliermarsh worked on recently? 🙏 Thank you for exploring StarSearch! We've invested our passion and creativity into this; your feedback is invaluable. Dive in, engage, and know we're here for any questions or chats about the wonders of OpenSauced. 👇 We're all ears for your feedback below! 👇

Congrats on launching StarSearch. It’s the Github Contributor Tab on steroids. This opens up so many opportunities for finding the right person for the right task. Even just searching for specific packages or components, I can easily identify the persons who are instrumental in the development.

This is so cool! I love the idea of knowing specifics around who contributed what. So huge!

his StarSearch feature sounds interesting, it can help me better understand the contributors in open-source projects. I'm looking forward to trying it out and discovering new contributors.

i had a lot of fun working on the user interface (UI) for StarSearch. One exciting challenge that I tackled was loading dynamic widgets into a StarSearch response depending on the StarSearch response returned. I think I came up with an elegant solution, but I’m always welcome to feedback. 😎 It’s still early days, but we’ll be adding more dynamic widgets over time now that the logic is in place in the code base. Stay saucy peeps!

It's been really cool to watch the process and growth of this feature. We've been able to identify information that wasn't readily available before. It was there, but you would have to dig deep and spend a lot of time to find the answers for it. I'm a big fan of community and building bridges and I think StarSearch offers a new way to connect people. It also offers a great way to support people and projects as well. You can ask questions like, "Is the Laravel project at risk?" It'll let you know what its lottery factor (risk if a top contributor leaves) is and who the top contributors are. If a project is at high risk because a top contributor is putting in most of the contributors, that's an opportunity to support their continued work. I'm looking forward to seeing the continued development of StarSearch!

This is great! Love OpenSauced 🔥

Amazing Work @bdougieyo @nickytonline @bekahhw and team! I showed this to a few product managers at my company and they loved it. Opens new possibilities for non-tech folks to estimate productivity and maybe even hire through open source instead of the standard coding interviews!

A few months ago, @bdougieyo came to me with what sounded like a big, crazy, amazing idea 🤔 We have ALL this public unstructured GitHub data. We've ramped up our data-pipelines to operate at GitHub's incredibly huge scale. We've even invented nuanced and unique metrics that can give very good insights into open-source communities. But what if we enhanced those mechanisms to work with AI capabilities? ✨ StarSearch is the result of months of work experimenting, living on the bleeding edge of AI technologies, and bringing a huge scale AI system to production. Ask StarSearch about projects you care about, things you're trying to work on, the Lottery Factor, and see what sorts of unique discoveries you can make! 🔧 I built the backend and data pipelines that make all this possible: StarSearch is a complex, multi-agent RAG (retrieval-augmented-generation) that has access to droves of our pristine GitHub data and other services. Several micro-services working together make this all possible: the "pizza-time" service consumes realtime GitHub events from the public GitHub events API. This populates the metrics, histograms, and time-series charts you see today on OpenSauced. Next, we have something called the "star-search-embedder" that looks for rows of data in our database that match the criteria we've set. It takes batches of those rows and embeds them into our vector store using a text embedding model. But first, we generate an AI summary on this unstructured texts in order to scrub them of any "messy" metadata or stuff we don't really need to embed. This is accomplished at-cost using a few GPUs on Kubernetes, vLLM, and open-source AI models. Then, within our API, we use a multi-agent architecture for our LLMs to enable a powerful question and answer engine. The agents have access to several of our other services and can "call" each-other to get necessary information from one agent to the other. For example, our internal "Bing Search AI Agent" knows how to interface with the Azure Bing search service, can generate summaries on mass amounts of raw, unstructured search results, and can hand those back to a calling agent that need made the query. More importantly, these agents can perform a vector-search on all those vectors we've embedded through our data pipelines. Today, we have over 100m+ vectors that power this engine and enable StarSearch to search through pull requests and issues. 🚀 One of my favorite queries to use is a sort of "needle in the hay-stack" search. Let's say I'm working at a product team shipping a Kubernetes platform. And I need to upstream some changes to how persistent storage volumes are claimed in the upstream kubernetes/kubernetes project: that's a very, VERY heavy lift if you've never worked in that community before! Where to even start!? What groups are involved? Who would be best to reach out to for feedback in the community? Where is the prior art? Asking StarSearch questions like "Who has worked on persistent volume claims in kubernetes/kubernetes?" can start to give you an idea of who those people might be, unlocking you to gain community support on a huge undertaking!! 🙏 Would love to hear any and all feedback!! Thanks all and stay saucey!

Huge! Excited for what insights we can pull as well as searching for the right people when leveraging a new open source package/project 🙌

Congrats on the launch @bdougieyo ! I just queried for some of the top contributors for one repo I was interested in and got good insights. I like how it not just shows the list, but a glimpse of their contributions, and an insight at the end

Killer!!! No more manual comparison shopping for libraries ever again!!

I normally spend hours in my week hunting for guests on CodingCat.dev podcast. Now I can find people so much easier. For example I gave this prompt today: "Who can I interview on my podcast CodingCat.dev about typescript projects that are trending" And got back: Here are several contributors to trending TypeScript projects that would make excellent guests on your podcast: @anonrig: Project: getsentry/sentry Contribution: Added more TypeScript rules to improve type checking and code quality. Summary: Anonrig submitted a pull request to enforce stricter TypeScript rules in the Sentry codebase, adding the @types/jest and ts-jest packages, and creating a new test suite. @Lightning00Blade: Project: puppeteer/puppeteer Contribution: Improved test reliability and added TypeScript types. Summary: Lightning00Blade worked on reducing test flakiness and adding TypeScript types, improving the development experience for those using TypeScript with Puppeteer. @ScreamZ: Project: amannn/next-intl Contribution: Updated documentation for TypeScript usage. Summary: ScreamZ enhanced the next-intl project documentation, offering better guidance on how to use TypeScript within the project. @jakebailey: Projects: microsoft/TypeScript-Website microsoft/TypeScript Contributions: Forced TypeScript to emit .d.ts files and linked changes with Microsoft's monaco-editor. Updated dependencies, switching back to TypeScript's bundler from esbuild. Summary: Jake Bailey has been active in both updating dependencies and linking TypeScript changes, focusing on improving the TypeScript development environment and its tooling. You can reach out to these contributors to share their insights and experiences on working with TypeScript on trending repositories.

Starsearch is a pretty cool feature! I can definitely see myself using it in the future when I want to maintain my own projects. Congratulations on the launch @bdougieyo

The product looks interesting, but I'm curious about the usage frequency of this product. How many people actually need it?

heads up. scrolling doesn't work in safari 😅 Like for this page: https://app.opensauced.pizza/use...

Great UI! Awesome team and one of those components you didn’t know you wanted and once you use it you don’t know how you lived without it!

Congratulations on the launch! I an impressed by the results I have gotten so far. Great job!

The best looking chat UI ever with a very novel use-case!! Awesome work guys 👏👏

Congrats on the launch Brian and the team.