Launching today
Osaurus
Open source agents that run 100% locally on your Mac
388 followers
Open source agents that run 100% locally on your Mac
388 followers
The native macOS harness for AI agents. Any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
Osaurus
Hey Product Hunt, I'm Terence, founder of Osaurus. I spent 20 years shipping software at Netflix, Tesla, and Zillow before going all in on this.
Own your AI. Osaurus is an open source AI agent platform that runs on your Mac.
MIT licensed, native Swift for Apple Silicon. No account, no subscription, no Electron.
We started as Dinoki, a 5MB desktop dinosaur, and grew into a full agent platform through open source community feedback. Now at 7K+ GitHub stars and 175K+ downloads — all by word of mouth.
The problem: most AI assistants run on someone else's server.
Your files, memory, and context leave your machine every time you use them, usually behind a monthly subscription.
Osaurus keeps all of it on your Mac.
What that means in practice:
Agents read your Calendar, look up Contacts, send iMessages, and work with your real files
An isolated sandbox writes and runs code, producing real files on your desktop: images, PDFs, presentations
Every action goes through an approval gate. You see what the agent wants to do before it does it
Local models run fully offline. We built our own Swift MLX runtime, no Python underneath
Want a frontier model? Bring your own key (OpenAI, Anthropic, Gemini) or use pay-as-you-go Osaurus Cloud. Either way, your memory and context stay local
It's free and always will be.
16GB of RAM gets you started with local models, 24GB recommended.
Try it at osaurus.ai. Download takes seconds, no account needed.
I'll be here all day answering questions. My favorite Osaurus hack is to set up Agent DB and self-scheduling to create a personal dashboard!
@tpae Cheers. Long time looking into this project and using it on my machine. It is really well thought out, detailed and with so many options and use cases. Best of all to you and everyone involved in the Osaurus project.
Osaurus
Hey @ruslan_mrsidze ! Thank you so much for your support. We're here because of you. Looking forward to doing more together. Stay tuned for some amazing updates!
@tpae Congrats!
I used to piece my AI system together from different apps just to get a working agent, but Osaurus was the all-in-one solution for me. It just works flawlessly.
For my use-case, I use it with a local AI as an autonomous assistant for my vacation rental business, so it helps me with emails, marketing and general organization.
Thank you so much for this project and good luck!
Osaurus
Hey@timon_135 ! Thank you so much for your support!
Glad it's working out for your business, if you have any feedback on how to make it better, we're all ears.
@tpae If I'm not mistaken, there are no projects in which I can upload all important files to which the agent always has access, correct? Each agent has his own memory here, which works great. But it's really helpful to be able to upload all relevant files in one project from the beginning. Otherwise everything is perfect and works great! :)
Osaurus
@timon_135 This is something we're working on! We're thinking of a wiki-like knowledge base where your agents can store and retrieve important information grouped by context or projects. This should also help you categorize them into projects too.
Raycast
So stoked to unveil @Osaurus to the Product Hunt community!
I've been a long-time advocate of open source (going back to the launch of @Mozilla Firefox in 2004!).
I've followed products like @Ollama and @LM Studio but neither is Mac-native nor have the character of Dinoki, the little guy I originally fell in love with, long before Petdex existed:
While I'm a big Anthropic and OpenAI user, I also believe strongly that local, open source AI is the future of computing, and Osaurus is the user-friendly app bringing this to everyone.
Osaurus is like the Firefox of open source AI!
You can download and run the latest models from @Z.ai @Qwen @Gemini (Gemma), or BYOK.
Now's an awesome time to give Osaurus a try, and if you're feeling bold — the beauty of open source means we'd love your contributions!
Osaurus
@ridhwikvinod Thank you! I would say 16GB would fit Gemma 4 e4b, which is not the most smartest but is pretty reliable at tool calling. For best experience, I would suggest 24GB.
Congrats on the launch! I like that it runs locally and asks for approval before each action. For anything touching Calendar, Contacts, and iMessage, that's the combination I'd want before granting access.Curious how you handle memory and context across sessions while keeping it all on-device.
Osaurus
Thank you@alieksia !
Everything is stored locally on your file system, including chat history, memory, and everything else. Your Mac has the capability to run it's own inferencing, it can distill memories too, and process it's own embeddings for dynamic contexts.
@tpae Huge congrats on bringing Osaurus to PH! 🎉
For users running hybrid workflows (e.g., small local model like Gemma for simple file/routing tasks, but switching to BYOK Claude/OpenAI for heavy reasoning), can an agent dynamically route tasks between local and cloud models within the same workflow, or is an agent fixed to one specific model backend?
Osaurus
@franz_briones Yes! We recently launched Subagents, which allows your agent to use local or remote model to delegate tasks to another local or remote model. It doesn't do intelligent routing yet, but if your reasoning model is capable of identifying which task is good for which model, should be able to set up routing logic via system prompts.
The approval gate is nice. One action, easy call. Wondering once an agent chains 15 steps to build a deck or deploy a site, does every step stop and wait for me? Fantastic launch!
Osaurus
@artstavenka1 Thank you so much! You can always "Always Allow" on some of those actions and it won't ask you again. I would leave the destructive ones to "Always Ask" just in case!
DiffSense
How good it the macuse skill? Can the mac be controlled via local LLM? or does that require better models only available via cloud? If local LLM is possible with mac-use skill, what requirment would support local mac-use skill? Btw looooooove the Laundromat Afternoon theme 😸
Osaurus
@conduit_design Great question! We run our own evaluation suite for each local model using community sourced compute. I have to say, it's decent enough to use, some models are better at it than others. Strange though, if it's good at computer use, then it's lacking in agentic coding, and vice versa. You might need to switch between two models to have best of both worlds.
https://github.com/osaurus-ai/osaurus/blob/main/reports/COMPATIBILITY.md