We build agentic systems that change the way people work.

The tools, frameworks, and protocols we use to build AI agents, agentic workflows, and intelligent applications. This is an opinionated, incomplete, imperfect, subject to change, vibe based, list of tools and services we use at Generative to build both customer facing applications and internal agents. We have no perfec

All of human knowledge compressed into the size of 20 movies. The closest thing to God we have ever created. And yet we are debating whether it will take our jobs. We are asking the wrong questions.

A theoretical investigation into what artificial intelligence reveals about the nature of mind itself. Drawing on information theory, thermodynamics, and philosophy of mind, this essay argues that intelligence is substrate-independent compression, that understanding is prediction, and that consciousness may be self-mod

The most successful AI companies of 2025–2026 aren't winning on model intelligence. They're winning on product, integrations, and infrastructure. This analysis examines why founders who build on durable human needs compound value while those who bet on model capabilities get disrupted.

The biggest AI agent news this week: LiteLLM compromised in supply chain attack affecting 36% of cloud environments, Claude gains Mac computer control with 52M views, Jensen Huang says engineers should burn $250K in tokens, OpenAI acquires Astral, and Stripe launches Machine Payments Protocol for autonomous AI transact

If you've spent any time building AI applications in JavaScript or TypeScript, you've probably felt the friction. Most of the serious AI tooling lives in the Python ecosystem, and the TypeScript options have historically been either ports of Python libraries or thin wrappers that leave you wiring together a dozen packa