Msty
banner
msty.app
Msty
@msty.app
Use online and offline LLM models without a headache. https://msty.app

By @ashokgelal.bsky.social & @nikeshparajuli.bsky.social

🇺🇸
Reposted by Msty
Run AI locally in 5 mins! No subscriptions, no data concerns - just your own private AI assistant with MSTY. Super simple setup, even offline chatting! https://youtu.be/xATApLtF92w #LocalAI #Privacy
March 6, 2025 at 9:28 PM
Msty App 1.8.0 is now available - full text search, Gemma3, Modular Rendering Engine, Mermaid Diagrams, Claude 3.7 Thinking, GPT-4.5. Preview and much more!

t.co/OGgID2NwPB
https://msty.app/changelog
t.co
March 13, 2025 at 12:29 AM
Here's a sneak peek at one of the many videos about Msty web! First one is the most important one - saving your data privately, securely BUT Locally!! More videos coming over the next few days that cover other new exciting features (4 videos up already).
Msty Studio - Intro
YouTube video by Msty App
youtu.be
March 3, 2025 at 11:19 PM
Reposted by Msty
Breaking AI Censorship: See how #perplexityai R1 1776 handles sensitive topics with surprising transparency, while DeepSeek R1 stays cautious. Side-by-side comparison reveals everything using Ollama and @msty.app youtu.be/MdI_qVHJSGg #AI #MachineLearning
Political Censorship in R1 is INCREDIBLE!!
YouTube video by Matt Williams
youtu.be
March 3, 2025 at 9:41 PM
Msty ver 1.7 is now available:

Toggle Model Providers, reasoning tokens for Open AI o[X] Models, DeepSeek as a Remote Models Provider, Model Instructions as Developer Prompts for Open AI o1 and o3-mini models, Updated Perplexity Model IDs, signed Windows installer, and more. 👇
Latest Msty Changelog
AI beyond just plain chat. Private, Offline, Split chats, Branching, Concurrent chats, Web Search, RAG, Prompts Library, Vapor Mode, and more. Perfect LM Studio, Jan AI, and Perplexity alternative. Us...
msty.app
February 10, 2025 at 6:45 PM
Less than half a week and we are back with new release ver 1.6 where we continue to improve our support for the new #reasoning #thinking models like #DeepSeek
January 30, 2025 at 3:10 PM
⚡️We have release 1.5.0 with new faster rendering engine, thinking reasoning tags, better RTD responses, better app performance, and a few more.

msty.app/changelog
January 26, 2025 at 2:50 PM
Reposted by Msty
Would love to see @msty.app mentioned in the survey. Regardless, please take a few minutes to fill up this survey if you are using Gen AI
January 24, 2025 at 11:27 PM
Reposted by Msty
on a daily basis I typically use @github.com copilot, and @msty.app for questions (mostly not about code).

I wouldn't use AI tools to bootstrap a new project - I enjoy doing it by hand too much.

if anyone (non-AI) offered to 'do' a first draft for me, I'd probably say no too ...

#ama

roe.dev/ama
January 24, 2025 at 10:54 PM
Reposted by Msty
I started out using @lmstudio-ai.bsky.social for running local models, but I recently switched to @msty.app. No issues. Document attachments and knowledge stacks improve the results. #AI #GenAI
peterwoods.online/blog/msty-cr...
MSTY Crash Course
earn how to use MSTY to simplify running local AI models. Explore features like side-by-side model comparisons, quick prompts, and an easy setup process.
peterwoods.online
January 24, 2025 at 4:30 PM
Reposted by Msty
Started testing out msty to test out LLM models and streamlit to stop me from pulling out my teeth with front end programming boredom. Respect to the engineers who have the patience for it and do a good job. If you’re in the product space and testing out llms Msty.app is worth a look 👀
January 2, 2025 at 6:13 PM
#DeepSeek Reasoning #R1 models are now available in Msty. You can find 7B reasoning model on the featured list and other models under #Ollama Models Hub.
January 21, 2025 at 1:44 PM
When the form meets the functions
January 12, 2025 at 6:26 PM
Wishing you all a very Happy New Year 2025, and thank you for making 2024 such an incredible year. It was wonderful having you here and getting to know so many of you - here and on our Discord server.
January 1, 2025 at 2:31 AM
🎁 Here's a few hours early Christmas Gift to you all! Msty 1.4 is now released! It brings a number of new features and improvements:
December 24, 2024 at 8:59 PM
🙏
December 18, 2024 at 7:55 PM
"This thing is awesome!!!!! This is my main going forward." blog.matthewrogers.org/b/7467C19D-2...
blog.matthewrogers.org
blog.matthewrogers.org
December 8, 2024 at 12:47 AM
Reposted by Msty
It’s even easier than that. Just use Msty.
December 4, 2024 at 4:06 AM
Reposted by Msty
Ollama WebUI (open source), AnythingLLM and Msty (I use this one) allow to do this in case if you need some inspiration
November 22, 2024 at 6:57 PM
Llama 3.3 70B, which is on par with Llama 3.2 405B is now available on Msty
December 6, 2024 at 6:29 PM
🚀 #Qwen 2.5 Coder Series Update! 🚀

All six sizes are now available on Msty

0.5B, 1.5B, 3B, 7B, 14B & 32B

🌟 Key Improvements:

* Enhanced Code Generation
* Superior Code Reasoning
* Advanced Code Fixing

🔥The 32B model matches OpenAI's GPT-4o in performance!🔥
November 11, 2024 at 10:04 PM
Reposted by Msty
In the upcoming release, @msty.app will indicate whether you can run a model on your machine. But instead of using just 🔴 🟡 🟢 traffic lights, we will show a "Compatibility Score" to help you understand how close (or far) you are to being able to run it. Score is shown for each quantization.
November 7, 2024 at 1:27 PM
Reposted by Msty
Also, if a company like Microsoft can't afford to make a purely native app and depends on ElectronJS for cross-platform, you can't blame indie devs like us to write one for each platforms. At least we work hard to make it look beautiful and functional (case in point @msty.app, @yaak.app)
November 4, 2024 at 9:10 PM
🦋
November 2, 2024 at 1:14 PM