Own your AI. Agents that remember, execute code safely, and stay reachable from anywhere -- all on your computer. Any model. No cloud required. Open source.

Joined May 2025
Osaurus retweeted
Replying to @OsaurusAI
@OsaurusAI does the muscle, Ornith does the hustle. 🙌 Two bros took all daily grind. Check out the amazing work from Osaurus team!! 🔗 osaurus.ai
Congrats to the Ornith team. Ornith-1.5-122B is a monster. It’s in Osaurus on day one. Running on a Mac, no cloud, no subscription. One prompt. It built a flying car game.
6
7
55
2,994
Osaurus retweeted
Osaurus for Windows has built-in privacy controls to protect your sensitive information. Watch an accountant’s workflow: Claude Sonnet 5.5 drafts a letter to the IRS while the client’s name, SSN, and other sensitive details never leave the PC.
3
3
1
18
1,319
Osaurus retweeted
SwiftUI is monumentally bad. One of the first things that I did for @OsaurusAI was to refactor every core feature to AppKit. The performance has been remarkable ever since
SwiftUI is not good. It's been 8 years. We all need to admit that it was ok when we were coding, and it's just plain bad now that agents are doing the work. UIKit/AppKit are simply better across the board in the agentic era.
1
1
3
298
Was fun working on this feature! Osaurus lets you keep your private life private even when using cloud models.
Osaurus for Windows has built-in privacy controls to protect your sensitive information. Watch an accountant’s workflow: Claude Sonnet 5.5 drafts a letter to the IRS while the client’s name, SSN, and other sensitive details never leave the PC.
1
4
369
Todos hablando de Grok Bot, Meta Muse, Open AI Dots. Pero yo uso @OsaurusAI con @deepseek_ai y no he necesitado nada más 🔥
1
4
239
I'm not playing around. Since releasing the beta yesterday, I've already added: - Persistent memory - Agent sandboxes (using WSL Containers) - Automations (folder watchers, scheduled tasks) - Bug fixes And there's lots more coming.
Osaurus Beta for Windows has support for WSL Containers on day one of its GA. Watch a local model safely experiment with python within a sandbox to generate a Mandelbrot fractal. Fully native, built for Windows with WinUI, C#, and .NET 10 xitter.cf/windowsblog/status/210…
1
4
8
1,831
This is why we're building @OsaurusAI You own your data. You own your inference (choose between local/cloud) You don't have to worry about someone training on your data, even if they claim they aren't. With local AI, your data stays on your device.
Don't use this Build your own software using their tokens So when their tokens become too expensive You can switch to your own GPUs Your compute. That you control So you yourself can't be controlled You need to control your stack -- or you become enslaved
2
6
608
#design #ux #ai #localai I just had a great conversation with the founder of @OsaurusAI I’ve been following the evolution of the app since the beginning of the year. They built Raptor models, and the results are impressive. osaurus.ai
1
1
5
384
Osaurus retweeted
Benchmarks measure what a model knows. Osaurus shows what it can do
Bonsai 2 dropped hours ago. It's already doing real work in Osaurus. Read two CSVs. Wrote the Python. Drew the chart. Then found the one channel losing money and told me why. 27B. Ternary. Nothing left the Mac.
1
2
429
Osaurus retweeted
dealign.ai
@dealignaiSep 18
A little verbose for my taste, but absolutely gets the job done. Try out the ~6gb and ~8gb quants of Bonsai 2 27b on your Mac!
Bonsai 2 dropped hours ago. It's already doing real work in Osaurus. Read two CSVs. Wrote the Python. Drew the chart. Then found the one channel losing money and told me why. 27B. Ternary. Nothing left the Mac.
2
3
51
6,637
Osaurus retweeted
Local AI shouldn't be limited to expensive hardware. Everyone should have the opportunity to own their AI.
Raptor 0.6 just shipped. Most Macs have 8 or 16 GB. Most AI models pretend they don't. Raptor is our agent model built for those machines. Reads folders, checks spreadsheets, drafts emails. Local, free. 3.7 GB, down 41% from the last version.
2
5
687
This will be coming to Osaurus for Windows as well. Not everyone has an RTX 30/40/5090. It'll open up local model usage for PCs with more common GPUs. You won't need a workstation to use local AI.
Raptor 0.6 just shipped. Most Macs have 8 or 16 GB. Most AI models pretend they don't. Raptor is our agent model built for those machines. Reads folders, checks spreadsheets, drafts emails. Local, free. 3.7 GB, down 41% from the last version.
1
1
7
1,264
Windows users deserve a great AI app that doesn't hog their system resources. I built the @Windows version of Osaurus to be fully native with a focus on user experience, performance, and ease of use with local models. I can't wait for you to try it and share your feedback!
It's here. The first fully native agent harness, built for Windows. No electron in sight. Osaurus for Windows is almost ready for beta. Get ready for a team of agents running right on your PC, local and private. Watch Qwen3.8-27B set up a team of agents to perform a code review.
6
6
3
49
5,435
Osaurus retweeted
dealign.ai
@dealignaiSep 15
Lets be honest, every other engine having so many flags to be able to even launch, then handling all the json configuration to connect to the harness so you can actually use it; who wants to really do all that? This has to for sure be the cleanest and easiest way to be able to just directly launch an LLM and use for real scenarios, now available for Windows! @SonofNun did some amazing work
It's here. The first fully native agent harness, built for Windows. No electron in sight. Osaurus for Windows is almost ready for beta. Get ready for a team of agents running right on your PC, local and private. Watch Qwen3.8-27B set up a team of agents to perform a code review.
1
3
11
2,205
Osaurus retweeted
dealign.ai
@dealignaiSep 3
Its time we focus on sub 24gb Mac’s - in this day and age, when someone goes and buys a $3000 Mac, while us local-pilled people understand that nearly all that matters is RAM and its speed, the main majority of people in the world consider and expect it to be a high end device - which when compared to the amount of raw compute you’d be able to get 5-10 years ago for that cost, it is. I will be focusing on our “mixture of models” theory; where a main orchestration/chat model spawns and delegates specifics tasks over to another model which specializes in that task and proceeds to act in a manner of; Main model 1 is unloaded -> task specific model 2 is loaded -> does task -> unload model 2 -> load model 1 back and resume I hope that over time this will be able to prove that its not a high parameter count that matters, but that having a handful of models which hyperfocus on specific topics being loaded and unloaded in an efficient manner can come to meet the needs of all automation.
Most Macs have 8 or 16GB. Model releases pretend they don't. About 40% of Osaurus users are on those machines. So we built them an agent model. It reads your files, checks your spreadsheets, drafts your emails. Raptor 0.5. 8B MoE. ~1B active per token. 6.3 GB. Resident all day. Free.
15
10
1
189
28,574
Osaurus retweeted
Replying to @OsaurusAI
@OsaurusAI is so damn good right now that if they ever add a feature for building apps, a LOT of apps are going to be in trouble. 😂 Seriously, Osaurus is absolutely on fire right now. 🔥
2
8
278
Osaurus retweeted
dealign.ai
@dealignaiSep 1
Prefix caching now stores BY TOOL CALL instead of BY TURN allowing for dramatically speedier prefill speeds. Memory allocator bug has been fixed to 8gb, compiled decode for hybrid and other models enabled by default. Will be focusing heavily in more optimizations where I can in the next few days.
Osaurus 0.24 is out. Say "ship the release." The Orchestrator hands it to your specialist agents, runs them in parallel, and brings back one answer. One ask. One conversation.
2
12
2,280
Osaurus retweeted
We just released the DSpark weights for Nanbeige4.2-3B (huggingface.co/Nanbeige/Nanb…).
Osaurus is coming to Windows. Same idea. Your agents, your files, your models, on your machine. This is a 3B model reading my spreadsheets and finding a margin problem I missed.
4
12
86
9,040
Excited to show what I've been working on lately! Giving local models a beautiful, native home on Windows. C#, WinUI, fully local. Fully private. Coming soon!
Osaurus is coming to Windows. Same idea. Your agents, your files, your models, on your machine. This is a 3B model reading my spreadsheets and finding a margin problem I missed.
5
8
2
84
6,003