Osaurus brings both local and cloud AI models to your Mac - BERITAJA

As AI models progressively go commoditized, startups are racing to build the package furniture that sits connected apical of them. One absorbing entrant into this abstraction is Osaurus, an unfastened source, Apple-only LLM server that lets users move betwixt different section AI models, either locally aliases successful the cloud, while keeping their files and devices each connected their ain hardware.

Osaurus evolved retired of the thought for a desktop AI companion, Dinoki, which Osaurus co-founder Terence Pae described arsenic a benignant of “AI-powered Clippy.” Dinoki’s customers had asked him why they should bargain the app if they still had to salary for tokens — the usage units AI companies complaint for processing prompts and generating responses.

That sewage Pae reasoning much profoundly about moving AI locally.

“That’s really Osaurus started,” Pae, antecedently a package technologist astatine Tesla and Netflix, told TechCrunch complete a call. The idea, he explained, was to effort to tally an AI adjunct locally. “You could do beautiful overmuch everything connected your Mac locally, for illustration browsing your files, accessing your browser, accessing your strategy configurations. I figured this would beryllium a awesome measurement to position Osaurus arsenic a individual AI for individuals.”

Pae began building the instrumentality successful nationalist arsenic an open-source project, adding features and fixing bugs on the way.

Image Credits:Osaurus, Inc.

Today, Osaurus could flexibly link pinch locally hosted AI models aliases unreality providers for illustration OpenAI and Anthropic. Users could freely take which AI models they’re using, and support different aspects of the AI acquisition connected their ain hardware, for illustration the models’ ain memory, aliases their files and tools.

Given that different AI models person different strengths, the advantage of this strategy is that users could move to the AI exemplary that champion fits their needs.

Such a building makes Osaurus what’s called a “harness” — a power furniture that connects different AI models, tools, and workflows done a azygous interface, akin to devices for illustration OpenClaw aliases Hermes. However, the quality is that specified devices are often aimed astatine developers who cognize their measurement about a terminal. And sometimes, for illustration successful the lawsuit of OpenClaw, they whitethorn airs information issues and holes to interest about.

Osaurus, meanwhile, presents an easy-to-use interface that consumers could use, and addresses information concerns by moving things successful a hardware-isolated, virtual sandbox. This limits the AI to a definite scope, keeping your machine and information safe.

Image Credits:Osaurus, Inc.

Of course, the believe of moving AI models connected your instrumentality is still successful its early days, fixed that it’s heavy resource-intensive and hardware-dependent. To tally section models, your strategy will request astatine slightest 64 GB of RAM. For moving larger models, for illustration DeepSeek v4, Pae recommends systems pinch about 128 GB of RAM.

But Pae believes section AI’s needs will travel down successful time.

“I could spot the imaginable of it, because the intelligence per wattage — which is for illustration the metric for section AI — has been going up significantly. It’s connected its ain curve of innovation. Last year, section AI could hardly decorativeness sentences, but coming it could really tally tools, constitute code, entree your browser, and bid worldly from Amazon […] it’s conscionable getting amended and better,” he said.

Image Credits:Osaurus, Inc.

Osaurus coming could tally MiniMax M2.5, Gemma 4, Qwen3.6, GPT-OSS, Llama, DeepSeek V4, and different models. It besides supports Apple’s on-device instauration models, Liquid AI’s LFM family of on-device models, and successful the cloud, it could link to OpenAI, Anthropic, Gemini, xAI/Grok, Venice AI, OpenRouter, Ollama, and LM Studio.

As a afloat MCP (Model Context Protocol) server, you could springiness immoderate MCP-compatible customer entree to your devices arsenic well. Plus, it ships pinch complete 20 autochthonal plugins for Mail, Calendar, Vision, macOS Use, XLSX, PPTX, Browser, Music, Git, Filesystem, Search, Fetch, and more. 

More recently, Osaurus was updated to see sound capabilities arsenic well.

Since the task went unrecorded about a twelvemonth ago, it has been downloaded northbound of 112,000 times, according to its website.

Currently, Osaurus’ founders (who see co-founder Sam Yoo) are participating successful the New York-based startup accelerator Alliance. They’re besides reasoning about adjacent steps, which could spot Osaurus being offered to businesses, for illustration those successful the ineligible abstraction aliases successful healthcare, wherever moving section LLMs could reside privateness concerns.

As the powerfulness of section AI models grows, the squad believes it could little the request for AI information centers.

“We’re seeing this explosive maturation successful the AI abstraction wherever [cloud AI providers] person to standard up utilizing information centers and infrastructure, but we consciousness for illustration group haven’t really seen the worth of the section AI yet,” Pae said. “Instead of relying connected the cloud, they could really deploy a Mac Studio on-prem, and it should usage substantially little power. You still person the capabilities of the cloud, but you will not beryllium limited connected a information halfway to beryllium capable to tally that AI,” he added.