As AI models become increasingly commercialized, startups are scrambling to build the layer of software that sits on top of them. An interesting entrant into this space is Osaurusan open-source, Apple-only LLM server that allows users to move between different local AI models, either on-premises or in the cloud, while keeping their files and tools on their own hardware.
Osaurus evolved from the idea for a companion AI for desktopsDinoki, of which Osaurus co-founded Terence Pae described as a sort of ‘AI powered Clippy’. Dinoki’s customers had asked him why they should buy the app if they still had to pay for tokens — the usage units that AI companies charge for processing prompts and generating responses.
This made Pae think more deeply about the operation of AI locally.
“That’s how Osaurus started,” Pae, previously a software engineer at Tesla and Netflix, told TechCrunch after a call. The idea, he explained, was to try to run an AI assistant locally. “You can do almost everything on your Mac locally, like browse your files, access your browser, access your system configurations. I thought this would be a great way to position Osaurus as a personal AI for individuals.”
Pei began building the tool publicly as an open source projectadding features and fixing bugs along the way.
Today, Osaurus can be flexibly connected to locally hosted AI models or cloud providers such as OpenAI and Anthropic. Users can freely choose which AI models to use and keep other aspects of the AI experience on their own hardware, such as the models’ memory or their files and tools.
Since different AI models have different advantages, the advantage of this system is that users can change the AI model that best suits their needs.
Such a structure makes Osaurus what is called a “braid” – a control layer that connects different AI models, tools and workflows through a single interface, similar to tools like OpenClaw or Hermes. However, the difference is that such tools are often aimed at developers who know their way around a terminal. And sometimes, as in the case of OpenClaw, they can create security issues and holes to worry about.
Osaurus, meanwhile, presents an easy-to-use interface that consumers can use and addresses security issues by running things in a virtual sandbox isolated from hardware. This limits the AI to a specific range, keeping your computer and data safe.
Of course, the practice of running AI models on your machine is still in its early days, as it is very resource-intensive and hardware-dependent. To run local models, your system will need at least 64 GB of RAM. To run larger models such as DeepSeek v4, Pae recommends systems with around 128GB of RAM.
But Pae believes the need for local AI will diminish over time.
“I can see its potential because the intelligence per watt — which is like the metric for local AI — has grown significantly. It’s on its own innovation curve. Last year, local AI could barely complete sentences, but today it can actually run tools, write code, access your browser, and order things from Amazon […] it just keeps getting better and better,” he said.
Osaurus today can run MiniMax M2.5, Gemma 4, Qwen3.6, GPT-OSS, Llama, DeepSeek V4 and other models. It also supports Apple’s core models on the device, Liquid AI’s LFM family of models, and in the cloud, can connect to OpenAI, Anthropic, Gemini, xAI/Grok, Venice AI, OpenRouter, Ollama, and LM Studio.
As a full Model Context Protocol (MCP) server, you can give access to your tools to any MCP-compliant client. Additionally, it comes with over 20 native plugins for Mail, Calendar, Vision, macOS Use, XLSX, PPTX, Browser, Music, Git, Filesystem, Search, Fetch and more.
More recently, Osaurus has been updated to include voice capabilities as well.
Since the project was released nearly a year ago, it has been downloaded north of 112,000 times, according to website. The app competes with other tools that allow you to run models locally, such as Olama, Missy, LM Studioand others, but offers a diverse set of features and presents itself as a more user-friendly option for non-developers as well.
Osaurus’ founders (including co-founder Sam Yoo) are currently participating in the New York-based startup accelerator Alliance. They are also considering next steps, which could see Osaurus offered to businesses, such as those in the legal space or healthcare, where running local LLMs could address privacy concerns.
As the power of local AI models grows, the team believes it could reduce the demand for AI data centers.
“We’re seeing this explosive growth in the artificial intelligence space where [cloud AI providers] they need to scale using data centers and infrastructure, but we think people haven’t really seen the value of local AI yet,” Pae said. “Instead of relying on the cloud, they can actually deploy a Mac Studio on-prem and it should use significantly less power. You still have the capabilities of the cloud, but you won’t be dependent on a data center to be able to run that AI,” he added.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.
