IA personal local-first, arquitectura y los movimientos del sector que no dejan de confirmar la apuesta. Escrito en Hong Kong.
Dos artículos independientes, uno de un boletín sobre la economía de los creadores y otro de una publicación para desarrolladores, llegan al mismo diagnóstico. Nadie ha ganado la carrera de los agentes de IA personal. El cuello de botella no es el modelo ni es el hardware; es si el agente tiene acceso a los datos reales del usuario. Ese es el problema en torno al cual está construido Ostler.
“Local-first” has become a polite lie in personal AI. Most products marketed as local actually keep the heavy lifting in the cloud, with the cache on your device. Ostler runs every component on a single Mac, the one the customer already owns. This is what local-first looks like when you build it honestly.
Kenan Saleh, de a16z Speedrun, esboza la próxima ola de la IA: agentes que monitorizan el contexto de forma continua, predicen lo que importa y actúan antes de que se les pida. Nombra dos productos que lo hacen; ambos están en la nube. Aquí está cómo se ve el observar-para-actuar cuando los datos nunca salen de la máquina del cliente.
The New York Times informa de abogados corporativos convertidos en porteros en reuniones virtuales, expulsando a los tomadores de notas con IA en la nube. El riesgo para el secreto profesional es arquitectónico, no editorial. Aquí está lo que cambia cuando el tomador de notas funciona en la propia máquina del cliente, con transcripción en el dispositivo mediante WhisperKit y un registro de consentimiento a prueba de manipulaciones.
Apple’s App Store privacy nutrition label is the only privacy disclosure surface in tech with structural enforcement. The Ostler iOS app declares zero tracking and no linked data, because there is no Ostler server to link data to. The architecture writes the label, not the lawyer.
A class action filed in California this month alleges that chatbot conversations have been routed through advertising trackers. The argument lands because chatbots are now the most intimate technology many people use. Privacy by policy cannot prevent this kind of leak. Only architecture can.
Three completely different vantage points have converged on the same architecture for personal AI over the past six months. Singapore's Foreign Minister using it daily on a Raspberry Pi. Andrej Karpathy describing it on stage. A founder shipping it to customers. They had no reason to agree. They did anyway.
Apple is about to concede the category. The fact that the most privacy-obsessed consumer-tech company on the planet cannot build a personal AI locally tells you exactly how large the market is, and why the local-first bet is the contrarian trade now being demanded.
On 21 April 2026, OpenAI released Privacy Filter as open weights under Apache 2.0. It runs locally, detects eight categories of PII, and slots directly into Ostler's ingest, diagnostic, and pre-flight pipeline. Here is why, and what the release signals.
On Dwarkesh Patel's podcast on 17 October 2025, Andrej Karpathy argued that a small reasoner with external memory beats a 1.8-trillion-parameter monolith. That is the architecture Ostler has been running since late 2025. Here is what it means for local-first personal AI.
After twenty years of giving my data to tech companies, I built a personal knowledge graph that runs entirely on a Mac Mini. This is the story of how it got here, and why it matters that nothing leaves the house.