Osaurus brings both local and cloud AI models to your Mac
Osaurus combines local and cloud AI models in a Mac app that keeps users’ memory, files, and tools on their own hardware.
As AI models increasingly become commoditized, startups are racing to build the software layer that sits on top of them. One interesting entrant into this space is Osaurus , an open source, Apple-only LLM server that lets users move between different local AI models, either locally or in the cloud, while keeping their files and tools all on their own hardware.
Osaurus evolved out of the idea for a desktop AI companion , Dinoki, which Osaurus co-founder 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 AI companies charge for processing prompts and generating responses.
That got Pae thinking more deeply about running AI locally.
“That’s how Osaurus started,” Pae, previously a software engineer at Tesla and Netflix, told TechCrunch over a call. The idea, he explained, was to try to run an AI assistant locally. “You can do pretty much everything on your Mac locally, like browsing your files, accessing your browser, accessing your system configurations. I figured this would be a great way to position Osaurus as a personal AI for individuals.”
Pae began building the tool in public as an open source project , adding features and fixing bugs along the way.
Today, Osaurus can flexibly connect with locally hosted AI models or cloud providers like OpenAI and Anthropic. Users can freely choose which AI models they’re using and keep other aspects of the AI experience on their own hardware, like the models’ own memory, or their files and tools.
Given that different AI models have different strengths, the advantage of this system is that users can switch to the AI model that best fits their needs.
Such a structure makes Osaurus what’s called a “harness” — 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, like in the case of OpenClaw, they may pose security issues and holes to worry about.
Osaurus, meanwhile, presents an easy-to-use interface that consumers can use and addresses security concerns by running things in a hardware-isolated, virtual sandbox. This limits the AI to a certain scope, keeping your computer and data safe.
Of course, the practice of running AI models on your machine is still in its early days, given that it’s heavily resource-intensive and hardware-dependent. To run local models, your system will need at least 64GB of RAM. For running larger models, like DeepSeek v4, Pae recommends systems with about 128GB of RAM.
But Pae believes local AI’s needs will come down in time.
“I can see the potential of it, because the intelligence per wattage — which is like the metric for local AI — has been going up significantly. It’s on its own curve of innovation. Last year, local AI could barely finish sentences, but today it can actually run tools, write code, access your browser, and order stuff from Amazon … It’s just 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 on-device foundation models, Liquid AI’s LFM family of on-device models, and in the cloud, it can connect to OpenAI, Anthropic, Gemini, xAI/Grok, Venice AI, OpenRouter, Ollama, and LM Studio.
As a full MCP (Model Context Protocol) server, you can give any MCP-compatible client access to your tools as well. Plus, it ships with over 20 native plug-ins for Mail, Calendar, Vision, macOS Use, XLSX, PPTX, Browser, Music, Git, Filesystem, Search, Fetch, and more.
More recently, Osaurus was updated to include voice capabilities as well.
Since the project went live nearly a year ago, it has been downloaded north of 112,000 times, according to its website. The app competes with other tools that let you run models locally, like Ollama , Msty , LM Studio , and others, but offers a differentiated feature set and presents itself as a more user-friendly option for non-developers, too.
Currently, Osaurus’ founders (who include co-founder Sam Yoo) are participating in the New York-based startup accelerator Alliance. They’re also thinking about next steps, which could see Osaurus being offered to businesses, like those in the legal space or in healthcare, where running local LLMs could address privacy concerns.
As the power of local AI models grows, the team believes it could lower the demand for AI data centers.
“We’re seeing this explosive growth in the AI space where [cloud AI providers] have to scale up using data centers and infrastructure, but we feel like people haven’t really seen the value of the local AI yet,” Pae said. “Instead of relying on the cloud, they can actually deploy a Mac Studio on-prem, and it should use substantially less power. You still have the capabilities of the cloud, but you will not 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 doesn’t affect our editorial independence.
StrictlyVC Athens is up next. Hear unfiltered insights straight from Europe’s tech leaders and connect with the people shaping what’s ahead. Lock in your spot before it’s gone.
OpenAI is reportedly preparing legal action against Apple; it wouldn’t be the first partner to feel burned Connie Loizos
OpenAI is reportedly preparing legal action against Apple; it wouldn’t be the first partner to feel burned
OpenAI is reportedly preparing legal action against Apple; it wouldn’t be the first partner to feel burned
How to turn off Instagram’s new Instants feature and retract photos you accidentally shared Aisha Malik
How to turn off Instagram’s new Instants feature and retract photos you accidentally shared
How to turn off Instagram’s new Instants feature and retract photos you accidentally shared
Musk’s xAI is running nearly 50 gas turbines unchecked at its Mississippi data center Tim De Chant
Musk’s xAI is running nearly 50 gas turbines unchecked at its Mississippi data center
Musk’s xAI is running nearly 50 gas turbines unchecked at its Mississippi data center
Spotify launches a Wrapped-style recap of your entire listening history Ivan Mehta
Spotify launches a Wrapped-style recap of your entire listening history
Spotify launches a Wrapped-style recap of your entire listening history
AI voice startup Vapi hits $500M valuation after winning Amazon Ring over 40 rivals Jagmeet Singh
AI voice startup Vapi hits $500M valuation after winning Amazon Ring over 40 rivals
AI voice startup Vapi hits $500M valuation after winning Amazon Ring over 40 rivals
Amazon launches 30-minute delivery across the US Sarah Perez
Amazon launches 30-minute delivery across the US
Amazon launches 30-minute delivery across the US
Fintech startup Parker files for bankruptcy Anthony Ha
Fintech startup Parker files for bankruptcy
Fintech startup Parker files for bankruptcy
Key takeaways
- Osaurus allows users to operate AI models locally, promoting greater control over personal data.
- The flexibility to connect to different models may boost AI adoption in small and medium-sized Brazilian enterprises.
- The open-source project can foster a local developer community, stimulating innovation.
Editorial analysis
The introduction of Osaurus into the Brazilian tech market represents a significant advancement in how users interact with AI models. The proposal to allow users to operate AI models locally while keeping their data and tools on their own devices is particularly relevant in a context where privacy and information security are growing concerns. This aligns with the demand for solutions that ensure greater control over personal data, a theme that resonates strongly in Brazil, where the General Data Protection Law (LGPD) imposes strict restrictions on the use of personal data.
Moreover, Osaurus's flexibility in connecting to different AI models, both local and cloud-based, could stimulate the adoption of AI technologies in small and medium-sized Brazilian enterprises. Many of these companies are still in the early stages of digitalization and could benefit from a solution that not only provides access to powerful AI models but also allows customization and control over how these models are used. This could drive innovation and competitiveness in the sector, especially in a market where digital transformation is a priority.
The fact that Osaurus is an open-source project is also a positive aspect, as it can foster a local developer community that contributes to the tool's improvement, creating a more robust and collaborative ecosystem. Brazil has an active developer community, and the possibility of contributing to a project aimed at democratizing access to AI may encourage more people to engage with technology.
Finally, it is important to observe how Osaurus positions itself against other AI solutions emerging in the market. The proposal of a "harness" that connects different AI models in an intuitive way could be a competitive differentiator, especially if the interface is indeed user-friendly for the average consumer. Osaurus's success will depend on its ability to adapt to user needs and stay ahead of security and privacy concerns, which are crucial for widespread acceptance in Brazil.
What this coverage includes
- Clear source attribution and link to the original publication.
- Editorial framing about relevance, impact, and likely next developments.
- Review for readability, context, and duplication before publication.
Original source:
TechCrunch AIAbout this article
This article was curated and published by AIDaily as part of our editorial coverage of artificial intelligence developments. The content is based on the original source cited below, enriched with editorial context and analysis. Automated tools may assist with translation and initial structuring, but publication decisions, factual review, and contextual framing remain editorial responsibilities.
Learn more about our editorial process