Open Source Startup Podcast

E203: From Sentry to Modem - Rethinking How Product Teams Listen

E202: How the Largest MLOps Community Was Built

E201: Building Your Agent Army with Paperclip

E200: Open Sourcing Warp’s Terminal

E199: Rethinking Infra-as-Code for the AI Era

E198: How Unikraft Launches AI Agents in

E197: The Evolution of Building Open Source Businesses from HashiCorp to Flox

E196: Shifting Developer Portals to Agent Portals with Port

E195: Taking on the New AI Attack Surface With Manifold: Runtime, Skills & Supply Chains

AI security is undergoing a fundamental shift from securing static model responses to protecting dynamic, agent-driven actions at the endpoint. This transition requires moving beyond traditional guardrail-based approaches toward comprehensive runtime detection and response. Manifold Security addresses this by prioritiz...

E194: Fal's Bet on Generative Media

Fal, a generative media cloud platform, successfully pivoted from a Python-based data transformation tool to a specialized infrastructure provider for AI inference. By prioritizing performance engineering and custom kernel development, the company addressed the lack of reliable, scalable APIs for image and video models...

E193: Managing 100s of Agents with Maestro

Maestro, an open-source desktop orchestration platform for AI agents, addresses the critical challenge of context management in generative AI development. By implementing a tab-based system, the platform allows developers to maintain isolated, focused contexts for distinct tasks, effectively preventing the "context rot...

E192: Creating Browser Use, Navigating Hyper Growth & Building in the Competitive Browser Automation Space

Browser Use enables AI agents to control web browsers through natural language, replacing brittle, manually written automation scripts. By leveraging AI models to interpret visual and HTML data, the platform allows users to execute complex, repetitive tasks—such as data extraction or form filling—without requiring trad...

E191: Super Fast Infra for Agents to Use the Internet

Kernel provides essential infrastructure for AI agents to navigate the internet, addressing the technical challenges of browser automation. By leveraging Chromium on Unikernels and Cloud Hypervisor, the platform achieves sub-20ms startup times, overcoming the latency issues inherent in traditional Docker-based browser ...

E190: Open Sourcing AI Coding Platform Devin to Create OpenHands

E189: Why Your Backup Platform Should Be Open Source with Plakar

E188: Building (And Spinning Out) Open Source Projects With Informal Systems

Exclusive: BYOC Vendor Nuon Goes Open Source!

E186: Unlocking Your Unstructured Data with Typedef

E185: The Challenges with Monetizing Open Source with the Creator of Rich + Textual

E184: Building the Browser for AI - the Browserbase Story