Open Source Startup Podcast

In this episode, our co-hosts Robby and Tim talk with Modem Co-Founder Ben Vinegar who's building the AI product manager for software teams. He was previously a longtime engineering leader at open source application monitoring software platform Sentry. Ben reflects on his journey from Disqus to nearly a decade at Sentry, where he became the company’s first VP of Engineering and worked across product development, SDKs, acquisitions, and incubation. He shares how the rapidly falling cost of software development with AI led him to build Modem, an AI product teammate that helps teams understand what customers are saying and connect that feedback to what they’re shipping.The conversation explores why data and context, not just the agent, are the hard parts of building useful AI products, how conversational data creates a new kind of observability, and why these systems are harder to build internally than they appear. He also discusses open source, dogfooding, and how being deeply fluent with AI is changing the way he hires and builds teams.

In our latest episode, co-hosts Robby and Tim talk with Demetrios Brinkmann, founder of the MLOps Community, the leading community for MLOps with over 90K developers in it today. He's also a Member of the Non-Technical Staff at the Agentic AI Foundation which is an open foundation advancing adoption of leading open source AI projects.This episode explores what it really takes to build a thriving community in a world where social media no longer provides the fast, meaningful feedback it once did. Drawing on lessons from growing the MLOps Community to tens of thousands of members, the conversation breaks down the difference between an audience and a true community, why consistency matters more than explosive growth, and why community-building is a marathon (not a sprint).The episode also covers the role of content, events, personal connections, and storytelling; why community shouldn’t be treated as another marketing channel; and why fostering community needs to be a company-wide effort rather than the responsibility of one community hire. Plus, it touches on the rapid growth of AI and agent communities, including MCP, and what founders can learn from them.

In this episode, our co-hosts Robby and Tim talk with Paperclip Co-Founder Dotta (Nate) whose viral agent orchestration platform has taken off over the past several months as more teams adopt agents at work. Their open source, also called paperclip, has >75K stars on GitHub and is becoming the de facto way to manage a team of agents. This episode explores what it really means to build an “agent-led company.” Rather than thinking of AI agents as isolated tools, Paperclip treats them like employees working toward shared goals, with the platform acting as the company that coordinates them. We discuss why existing AI workflows (whether it’s dozens of Claude Code tabs or standalone coding agents) break down at scale, and how Paperclip provides a unified interface for managing projects, agents, tasks, context, and budgets across any model or AI harness. From marketing and documentation to customer support triage and software development, the conversation dives into how teams can assign the right agents to the right work while keeping humans in control through evaluation, reflection, and orchestration.We also unpack the challenges and opportunities of building an open source agent platform in one of AI’s fastest-moving markets. The discussion covers Paperclip’s explosive early growth, the realities of maintaining a ton of community pull requests, security risks in agentic systems, and why the future isn’t about replacing people with AI - it’s about enabling individuals and organizations to scale their impact through coordinated agents. Looking ahead, we explore Paperclip Cloud, enterprise workflows, governance, and why the next frontier for AI isn’t just better models, but better memory, context, and systems for managing an entire workforce of agents.

This episode has our co-hosts Robby and Tim in conversation with Warp founder Zach Lloyd as he shares the company story and decision to open source their core product: the terminal. They now provide an open source agentic development environment (born out of the terminal) which is also called warp and has almost 65K stars on GitHub. Zach discusses his frustration with the traditional terminal and how it inspired him to rebuild it from first principles. Originally conceived before ChatGPT as a more intuitive, collaborative command-line experience, Warp quickly resonated with developers and has since grown to 1 million users. Lloyd discusses the company’s decision to build Warp in Rust, its early reluctance to open source the product, and how the rise of coding agents transformed Warp from a modern terminal into a broader agentic development environment.The conversation also explores Warp’s evolving product vision: a terminal, agent harness, and cloud platform that can orchestrate different models and coding tools without locking companies into a single provider. Lloyd explains how Warp uses agents to triage issues, write and review code, test interfaces, and accelerate open source contributions while keeping humans involved in key decisions. Ultimately, the episode is about how AI is reshaping software development and Warp’s ambition to become the platform that turns ideas, community feedback, and company workflows into shipped software as efficiently as possible.

This Open Source Startup Podcast episode has our co-hosts Robby and Tim in conversation with Pavlo Baron from Platform Engineering Labs - creators of open source infra-as-code platform formae. This podcast explores why traditional infrastructure-as-code tools like Terraform and Pulumi can struggle with state, drift, and the disconnect between code and real-world infrastructure. Pavlo shares lessons from building Instana and explains how those experiences led to Formae, an open-source approach that treats infrastructure state as accessible, executable code using Apple’s Pkl language.The conversation also looks at what infrastructure management needs in the AI era. By reducing low-level complexity and giving both humans and AI agents safer abstractions for discovering, modifying, and reconciling infrastructure, Formae aims to make infrastructure automation more reliable and less labor-intensive.

Dr. Felipe Huici, CEO of Unikraft and researcher-turned-founder behind the Unikraft unikernel project. He discusses tiny, sub-10ms VMs for AI agents, VM-grade isolation and fast checkpoint/resume, and how lightweight virtual machines enable massive scale, lower latency and cost, plus challenges like GPU access, snapshotting and integrating with existing cloud workflows.

James Bayer, product leader who helped scale Cloud Foundry, Pivotal, and HashiCorp and now CPO at Flox. He traces building sustainable open source businesses and the multiplayer vs single-player monetization model. He explains why Nix is powerful but hard, and how Flox makes reproducible, team-friendly Nix environments, automation for fleets, and AI-ready stacks for diverse hardware.

Zohar Einy, co-founder and CEO of Port, a builder of agentic SDLC and developer-portal infrastructure. He discusses evolving developer portals into agent-friendly platforms, the concept of a unified context lake for agent workflows, open-source integrations that feed agents, and governance and permissions needed to safely scale agent activity.

Oleks Yaremchuk, co-founder of Manifold Security and AI security engineer, and Neal Swaelens, co-founder and runtime security lead, discuss AI agent runtime and supply chain risks. They cover why runtime detection matters, how Manifest maps skills and plugins, lessons from open projects like LLMGuard, and strategies for building trustworthy AI security products. Short, technical, and forward-looking.

Batuhan Taskaya, founding engineer and Head of Engineering at Fal who built its inference engine and compilers, discusses building a generative media cloud. He explains why Fal focused on images before expanding to video and audio. Batuhan highlights deep systems work: custom runtimes, kernel optimizations, profiling to boost GPU utilization, and running diverse open-source models at scale.