Msty
@msty_app
Followers
391
Following
2
Media
51
Statuses
206
The simplest way to use online + offline AI Models on your computer. Offline First, Online Ready! Built by @ashokgelal @nikesh_parajuli
Your Desktop
Joined January 2024
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Labor Day
• 193670 Tweets
DAY6
• 164302 Tweets
Watch Sant Rampal Ji YouTube
• 128528 Tweets
#خلصوا_صفقه_موليرو_للهلال
• 109575 Tweets
#海のはじまり
• 82889 Tweets
Osimhen
• 81726 Tweets
写真・動画
• 81004 Tweets
BUMP
• 73797 Tweets
#CDTVライブライブ
• 66703 Tweets
데이식스
• 66153 Tweets
सुप्रीम कोर्ट
• 51053 Tweets
CONGRATULATIONS JIN
• 43253 Tweets
憲法改正
• 28787 Tweets
strawberry
• 27870 Tweets
弥生さん
• 15136 Tweets
#Galeno_to_ittihad
• 15012 Tweets
海ちゃん
• 14084 Tweets
DUNK SMN EP5
• 12676 Tweets
アカシア
• 11630 Tweets
PHUWIN SUMMERNIGHT EP5
• 10754 Tweets
ユミアのアトリエ
• 10636 Tweets
SB19 PAGTATAG BLOCKBUSTER
• 10220 Tweets
We are now available on
@huggingface
as one of the approved Local Apps which means now you can launch any models in Msty directly from within HuggingFace.
Please do us a favor and set Msty as your favorite Local App in your HF settings. We know it already is your favorite app :)
0
8
30
The next release will include this small but a very powerful toggle button. With just a click, you can make your Msty Local AI service available on the network, which means let it run on a powerful machine and interact from anywhere even from a mobile device.
1
0
14
A new, unique, and a giant feature is now being tested internally. No time to rest though. We are now tackling 2 big new features. The next release is going to be 🔥
2
2
12
Msty 0.9.0 is here bringing in many new features and improvements:
🤗 any
@huggingface
models
🦙 all
@ollama
models
🈁 reranking with
@JinaAI_
🔀 all models from
@OpenRouterAI
👐🏽 any OpenAI compatible providers including
@deepseek_ai
💄 Revamped Local AI UI
And a lot more!
3
3
12
Version 1.0 of Msty is now available! It brings in so many new features such as real time data, improved Knowledge Stack, New Attachments UI, new settings UI and oh so much more that even just the highlights turned out to be a full blog. 👇
7
1
8
While Meta prepares for a even bigger model, OpenAI casually drops a smaller but a powerful model.
#GPT4O
mini is available in Msty already!
✅ Text and Vision
✅ Solid Performance - reasoning, math, coding, multimodal reasoning
✅ Cheap
✅ Video, STT, & TTS coming soon! 🤯
Introducing GPT-4o mini! It’s our most intelligent and affordable small model, available today in the API. GPT-4o mini is significantly smarter and cheaper than GPT-3.5 Turbo.
159
616
3K
0
3
8
We are so grateful! Thank you!!
A second batch of local Generative AI apps are now live on compatible model pages on
@huggingface
🔥
Welcome to the family, friends 🥰
5
24
148
0
0
6
Fabric prompts are 🔥 and this is going to take your prompts game to the next level🪜
One click is all it takes!
In the next version, you'll be able to directly import Fabric prompts into
@msty_app
with just a click! It will download the prompts, fix the title, clean the content, and have it ready in just seconds.
Importing prompts from a folder will be possible as well.
0
2
3
1
2
7
#Gemma
2 is now available on Msty as well!
We make it very easy to use local as well as online LLMs on your machine.
✅ Offline First, Privacy focused
✅ Split chats with multiple LLMs
✅ RAG
And much more...👉
Gemma 2 is officially here! 🥳
Available in both 9B and 27B parameter sizes, Gemma 2 is higher performing than ever before. Download the weights on
@Kaggle
and
@HuggingFace
, or access the models in Google AI Studio.
Learn more →
63
291
1K
2
1
7
Introducing 2 new and very unique features - Delve mode and Flowchat.
3
1
6
Qwen has been one of our top 3 go to models and a model that we always recommend when being asked. It is really really good and Qwen 2 seems to be even better. In case you haven't noticed, it has been available in Msty as soon as it came out!
💗Hello Qwen2!
Happy to share the Qwen2 models to you all!
📖 BLOG:
🤗 HF collection:
🤖
💻 GitHub:
We have base and Instruct models of 5 sizes, Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B,
38
152
622
0
0
5
“Msty is the simplest to configure and has most of the features anyone would want from an LLM app“ A quick overview of Msty by
@aicodeking
#ollama
#openai
#groq
0
1
5
We hit a small milestone today - our Discord community is now 1000 members strong 🙏
0
1
6
We now have an official YouTube channel and our first video is about an upcoming exciting new feature in Msty. Go watch it here and please like and subscribe:
1
2
6
Msty Release day!!
The latest version comes with RAG feature - chat with your documents including Obsidian vaults🤯. Other features include
@perplexity_ai
API, search, concurrent chatting with local models using
@ollama
, split branching, and so much more!
1
0
6
We tried asking Llama 3 about Msty and it failed so bad we wanted to cry 😭
But then...
1
1
6
A new video is out where we talk about our upcoming new and improved settings UI
0
0
5
👀 🐐
Cooking something cool for next version of
@msty_app
. Just one of a handful new features in the pipeline for ver 1.1
0
1
5
4
2
5
🫡🇰🇷
The past few days, we noticed a sudden and huge spike in traffic from South Korea and couldn't figure out why... Turns out a popular Korean YouTuber has been making some amazing videos about Msty, driving all kinds of engagement our way!
0
0
3
0
0
5
In the next version of Msty, you'll be able to use any gguf models from
@huggingface
. And for your convenience, Msty will make the model compatible with
@ollama
. It would be as if you `ollama create` a model right within Msty.🤗🦙
2
0
5
Sonnet 3.5 is 🤯 It is now available on Msty!
Introducing Claude 3.5 Sonnet—our most intelligent model yet.
This is the first release in our 3.5 model family.
Sonnet now outperforms competitor models on key evaluations, at twice the speed of Claude 3 Opus and one-fifth the cost.
Try it for free:
450
2K
7K
2
1
5
Now that
#Llama3
70B is out, we decided to see how well it fares against GPT-4 Turbo and Gemini Pro. Overall it's pretty darn good!
0
0
4
Mistral's first code model,
#Codestral
, is now available on Msty both as through their API and as a local LLM.
1
0
5
One of the users of Msty made this review of Msty. Go check it out:
0
2
4
We took
@MistralAILabs
's new Cadestral model and compared it against GPT-4o to see how good it is at what it is made for - coding tasks. And we found it to be very powerful, accurate, and surprisingly, very concise. If you are interested in reading more and see some results👇🏽
1
0
3
Us trying to rescue them by telling they should have been using Msty all along to not be in this situation in the first place.
#chatgpt
1
0
3
And out of nowhere the latest version of Msty shows up. It brings support for head exploding speed from
@GroqInc
and head spinning latest models from
@AnthropicAI
and there are a few others for Ollama such as StarCoder2, dolphincoder and more!
1
2
3
🔥coming to Msty soon!
Phi3 vision was just released - it is just 4.2b params and extremely impressive. 🤩
I feel this is a breakthrough for low-latency/live inference on image streams - just imagine what even smaller/more specialized versions of this will enable in robotics! 🤯
4
24
77
0
0
3
New Prompts Library UI, transcriptions, Command R from
@coherenare
some of the highlights of the latest version of Msty
1
0
3
Msty will give you some insights about your RAG stacks. This is just the beginning and we plan to improve this further giving you even more insights about your RAG.
#comingSoon
#rag
#RAGDoneRight
1
0
2
👀
Started working on the new release notes. We added so many and yet found ways to remove so much. Any day now!
0
0
2
0
0
2
Just to be clear, we are doing early access beta testing right now and will be releasing to all our users very soon.
3
0
2
🧽🧼🫧
After working on
@msty_app
for almost 6 months with a neck break speed, it was about time we paid some technical debt. We spent 2 days last week doing so and couldn’t be happier with the state of code now - less files, more consistency. And now back again on churning features 🧹
2
0
6
1
0
2
"This might not make it to the release" 🤬 Ship it already!
One of the users shared a screenshot of comparing the outputs from different models using Msty's split chat feature. I looked at the screenshot and wondered if the experience could be improved a bit. 👇
1
0
2
0
0
2
We gave our site some face lifting over the weekend. Got to keep it fresh! 💅💄
1
0
2
A new icon has just appeared on the sidebar in the latest internal build of Msty. I wonder what this would do 🤔
0
0
2
So surprised and humbled to be on someone’s top of the list for an app that is just about a month old. We are into something! And we got more to come. 💪
0
0
2
Another small but very impactful feature - you will be able to split contents by either Characters (recursively + overlapping) or by Sentences.
We know
@Technovangelist
thinks that RAG is no good with character splitting so we wouldn't ship this without Sentence splitting 😅
0
0
1
@BardzoKurwa
Being able to use any ggufs from
@huggingface
is coming in a couple of days. Hop on our Discord if you want to try out a prerelease build
0
0
0
@casadeian
Hit CTRL and PLUS keys multiple times CTRL + and that should increase the size of everything. It's similar to zooming in on a maps app.
1
0
1
@findpurpose
Absolutely! What models do you use mostly? We can help you right now without waiting for us pushing an update. Mind hoping on our Discord to get this resolved right away?
1
0
1
@cibernicola_es
Ah! Just noticed the same handle. Got deceived with the profile pics :) This time we'll include you in the beta test for sure. Need to fix a couple of things first before the next round.
1
0
1
Coming to Msty soon!
Announcing Codestral: our first-ever code model.
- Open-weights under the new Mistral AI Non-Production License
- New endpoint via La Plateforme:
- Try it now on Le Chat:
18
161
768
0
0
1
@JoakimThomsen
Sending those files as attachments to the model? This is only possible with some online LLM providers. It is on our list but not implemented yet. What models/providers are you using?
1
0
0
Read up on how Sujita, a fictional Online Course Instructor who is teaching three Power BI classes, would use Msty and
@MistralAI
to prepare for her course work without having to worry about cost, and most importantly, privacy.
0
0
2
Oh and revamped Prompt Library, system prompts and much more. Check out a list of everything that’s new:
0
0
1
Msty 1.0 highlights blog post:
What’s New video:
Full changelog:
0
0
1
@JoakimThomsen
Ah! Not right now. We have folders that you could add as a knowledge stack and after composing you can start chatting. One technical limitation is that it doesn’t have auto sync right now. We are looking into it though.
1
0
1
@stuli1989
Please let us know how much she likes it, how much of hallucinated info she is getting, and mostly if she has any feedback for us in how we could make improvements.
0
0
1
@ClementDelangue
@Gradio
@argilla_io
You guys need a great app that you can call your own and something that is already integrated with HF 🤝. We just happen to know one. Just saying 🙃
0
0
1
Go check it out and let us know what you think.
0
0
1
@stuli1989
Hi! When there is an LLM involved, hallucination is always possible, unfortunately. You could minimize it by using a good model for inference, tweaking the prompt and some configs such as setting temperature to 0, etc.
1
0
1
Qwen is surprisingly a very good model
Now Qwen1.5-110B is on the top among pretrained models in Open LLM Leaderboard😉
14
26
187
0
0
1
