Open Source Startup Podcast

Kostas Pardalis and Yoni Michael, co-founders of Typedef, discuss their journey from major data infrastructure firms to creating solutions for unstructured data. They reveal how traditional systems like Spark fail under current AI demands and introduce Fennec, a tailored DataFrame library for LLMs. Insights on optimizing agentic systems and early go-to-market strategies add depth to their conversation. They also ponder the future of AI in data workflows and critique the explosion of benchmarks in the industry.

In this enlightening discussion, Will McGugan, creator of Rich and Textual, shares his journey in open source and building developer tools. He reveals the challenges of monetizing open-source projects, emphasizing the need to prioritize killer products over technical perfection. Will discusses the importance of the terminal as a fast interface and introduces Toad, a promising AI front end aimed at enhancing terminal workflows. With key lessons on hiring, simplifying operations, and early monetization, he offers invaluable insights for aspiring tech entrepreneurs.

In a fascinating discussion, Paul Klein IV, Founder & CEO of Browserbase, dives into the future of AI-driven browser automation. He reveals how Browserbase transforms traditional web browsers with its open-source Stagehand SDK, allowing developers to create automations using natural language. Paul emphasizes the importance of minimal feature bloat and community-driven design. He also introduces 'Director,' a low-code tool for non-developers, and discusses the ethical implications of automation, AI's relationship with the web, and the potential for innovative breakthroughs.

Vaibhav Gupta, Co-founder and CEO of Boundary, shares insights on creating BAML, a programming language designed for AI agents. He discusses the challenges of messy AI-generated code and how BAML offers a cleaner, more elegant alternative. Vaibhav highlights the importance of code quality and observability, emphasizing that beautiful code leads to fewer bugs and better functionality. The conversation touches on the limitations of using English for programming and why a dedicated language is essential for performance and debugging.

Yury Izrailevsky, co-founder of ClickHouse and former engineering leader at Google and Netflix, discusses the rapid rise of ClickHouse, an open-source OLAP database. He shares its origins at Yandex and highlights its unique columnar storage that optimizes performance and cost. Yury explains the shift to a managed cloud product and ClickHouse’s appeal in handling AI workloads. He also touches on building a remote-first culture and the company's successful integration strategy, making ClickHouse a favorite for companies like Tesla and Canva.

Chang She, Co-Founder and CEO of LanceDB, dives into the transformative power of multimodal AI, highlighting its applications in autonomous vehicles. He shares insights about the revolutionary Lance format that achieved a staggering 9,000% performance gain in real-time analysis. The conversation also covers the trust-building process in open source and the importance of integrated workflows beyond traditional vector databases. Looking ahead, he discusses emerging trends in AI, like audio infrastructure and the challenge for vector databases to evolve or face irrelevance.

Ryan Djurovich, Founder & CEO of Nadrama, dives into the complexities of Kubernetes and why simplifying it is crucial for developers. He discusses the challenges of setup and operations, aiming to streamline processes to enhance developer experience. Djurovich shares insights on the core value of Nadrama, focusing on abstracting infrastructure pain. He also emphasizes the importance of community engagement in product development and his commitment to baseline security informed by his Cloudflare experience.

Morgante Pell, Founder of Grit, an AI agent company focused on software maintenance, shares insights on automating software maintenance with LLMs. He discusses Grit's innovative tool, GridQL, designed for reliable code transformations, and the company’s motivation for going open source. Pell also highlights the challenges posed by AI-generated code in software maintenance and reflects on the strategic acquisition by Honeycomb, emphasizing the importance of building relationships in tech negotiations.

Emma Burrows is Co-Founder & CTO of Portia AI, the platform to build AI agents in regulated environments. Their open source Python SDK provides a developer framework for predictable and stateful agentic workflows. Portia AI has raised around $5M from investors including General Catalyst and First Minute Capital.In this episode, we dig into:Why they built an end-to-end platform from agent planning to deployment The focus on accuracy as their true north star metric Their paid contribution program How their found their initial ICP in regulated industries Why 2026 will be the year of agents Her best fundraising advice (hint: never really stop fundraising)

Alan Braithwaite, Co-Founder & CTO of RunReveal, discusses the evolution of modern security tools and why teams are reevaluating their data management strategies. He shares insights on the advantages of building RunReveal on the open-source ClickHouse database, enhancing flexibility for security teams. The conversation dives into their commitment to open sourcing and community engagement through innovative projects. Additionally, Alan highlights the transformative role of AI in automating security investigations and the importance of educating teams on these new technologies.