IA personnelle local-first, architecture et les mouvements du secteur qui confirment sans cesse le pari. Écrit à Hong Kong.
Deux articles indépendants, l'un issu d'une newsletter de la creator economy, l'autre d'une publication pour développeurs, aboutissent au même diagnostic. Personne n'a remporté la course à l'agent IA personnel. Le goulet d'étranglement n'est ni le modèle ni le matériel ; c'est de savoir si l'agent a accès aux données réelles de l'utilisateur. C'est précisément le problème autour duquel Ostler est conçu.
“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, d'a16z Speedrun, esquisse la prochaine vague de l'IA : des agents qui surveillent le contexte en continu, anticipent ce qui compte et agissent avant qu'on le leur demande. Il cite deux produits qui le font ; tous deux passent par le cloud. Voici à quoi ressemble l'observer-pour-agir quand les données ne quittent jamais la machine de l'utilisateur.
Le New York Times rapporte que des avocats d'affaires se transforment en videurs lors des réunions virtuelles, expulsant les preneurs de notes IA hébergés dans le cloud. Le risque pour le secret professionnel est architectural, pas éditorial. Voici ce qui change lorsque le preneur de notes s'exécute sur la propre machine de l'utilisateur, avec une transcription sur l'appareil via WhisperKit et un journal de consentement infalsifiable.
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.