Products·2 min read
By BitsMindsSource: TechCrunch

Osaurus Lets Mac Users Mix Local and Cloud AI Models in One Sandboxed App

Built by ex-Tesla and Netflix engineers, Osaurus routes between local Llama, DeepSeek V4, and Gemma 4 and cloud GPT-5.5, Claude, and Gemini in one sandboxed macOS app — with 112K downloads so far.

Osaurus Lets Mac Users Mix Local and Cloud AI Models in One Sandboxed App
Share:

A pair of ex-Tesla and Netflix engineers have shipped Osaurus, an open-source macOS app that finally treats local and cloud AI models as interchangeable rather than as separate worlds. The app lets a user flip between an on-device Gemma 4 running on their own M-series chip and a cloud-hosted Claude or GPT-5.5 within the same conversation, while keeping the user's files, memory, and tool calls scoped to their own hardware via a sandboxed virtual machine.

Co-founders Terence Pae and Sam Yoo originally built a desktop AI companion called Dinoki, then rebuilt it as Osaurus once it became obvious that the bigger problem for Mac users was not which model to run, but how to compose models, files, and apps without leaking data to a half-dozen vendors. The current build ships with more than 20 native plugins — Mail, Calendar, Vision, Browser, Git, and others — alongside a full Model Context Protocol server, so anything that speaks MCP can plug straight in. Local model support covers MiniMax M2.5, Qwen3.6, GPT-OSS, Llama, DeepSeek V4, Apple's on-device models, and Gemma 4; cloud routing handles OpenAI, Anthropic, Gemini, xAI/Grok, and OpenRouter behind one interface.

The pitch is positioning rather than benchmark. Osaurus is not trying to beat Ollama or LM Studio on raw model throughput; it is trying to be the layer above them — an ordinary-user shell where switching between local privacy and cloud capability is one click, and where the integrations matter as much as the model. The hardware bar is steep: 64GB of unified memory minimum, with 128GB recommended once users start loading DeepSeek V4. That positions Osaurus squarely at the new tier of M-class Macs that Apple has been pushing into developer hands ahead of WWDC in June.

Adoption is already non-trivial. The app has been downloaded more than 112,000 times since its release just under a year ago — modest by App Store standards, but extremely high for a developer-skewed local-AI tool. That gives Pae and Yoo a beachhead at exactly the moment Apple is widely expected to use WWDC 2026 to reveal a Google-Gemini-powered Siri overhaul and a deeper opening of its on-device AI stack. If Apple commodifies cloud-routing into the OS, Osaurus has to climb up the stack. If Apple doesn't, the gap it is filling becomes bigger, not smaller.

Want AI news before everyone else?

The morning's most important AI stories, straight to your inbox. No fluff.

Related Articles

Astra for Law: finding legal authority in a dedicated index In a dark burgundy law library, an open volume of case law lies on a walnut desk. A brass magnifying glass enlarges highlighted passages, connected by a fine gold line to a translucent legal search panel with the OpenAI emblem. The panel lists case law, statutes and regulations and displays 230 million plus indexed URLs, the corpus size cited in the article. Book spines repeat these source categories. The visual represents source retrieval and research; its illustrative page marks are not real case citations, and it does not imply that every answer is correct. Original editorial SVG for BitsMinds, openai-astra-for-law-legal-search-index. 18 September 2026. Conceptual legal-research illustration, not a product screenshot. Corpus size comes from the article. Astra for Law LEGAL RESEARCH CASE LAW STATUTES REGULATIONS U.S. LAW Astra for Law LEGAL SEARCH INDEX Search U.S. legal sources Case lawStatutesRegulations 230M+ INDEXED URLs CASE LAW AUTHORITIES & CITATIONS CASE LAW AUTHORITIES & CITATIONS U.S. CASE LAW · STATUTES · REGULATIONS BITSMINDS.COM
Products

OpenAI’s Astra for Law Scores 54% on Legal Research

Perplexity Portable Computer: the agent moves onto your PC An editorial illustration of a Windows workstation at night. The monitor shows Perplexity Portable Computer and a local task sequence. Beside it, the transparent side of a desktop tower reveals an illuminated Perplexity emblem, a circuit board and an RTX graphics card marked 24GB plus VRAM. A faint cloud and a closed permission gate sit in the background. Cyan and green light bring the on-device computing hardware into focus. The machine and interface are conceptual, not a specific commercial PC or an actual product screenshot. BitsMinds editorial illustration for perplexity-portable-computer-windows-rtx. Original vector artwork, 16 September 2026. PERPLEXITY / LOCAL AI BY PERMISSION perplexity ON DEVICE Portable Computer Your agent. Your hardware. Windows LOCAL RUNTIME LOCAL AGENT RTX LOCAL COMPUTE 24GB+ VRAM ON DEVICE BITSMINDS.COM PORTABLE COMPUTER / WINDOWS + RTX
Products

Perplexity's Local AI Agent Lands on Windows RTX PCs

APPLE · iOS 27 — 14 SEPTEMBER ChatGPT Gemini Claude Apple's Siri reset finally ships BITSMINDS.COM
Products

Apple Ships iOS 27 and Its Gemini-Powered Siri AI