←
AnythingLLM84 posts
AnythingLLM avatar

AnythingLLM

@AnythingLLM

All-in-one Desktop AI assistant. Private RAG, any LLM, Agents, and more. Open source: github.com/Mintplex-Labs/any…

◷ Joined August 2023▧ 9 Photos and videos
AnythingLLM avatar
AnythingLLM@AnythingLLM·Oct 13

As of Desktop v1.18.0 we now run models via llama.cpp instead of Ollama. • Up to 2x faster inference, depending on your hardware • A runtime install that’s ~13x smaller • Day 0 support for new models Blog: anythingllm.com/blog/lemonad…

Tim Carambat avatar
⟳ AnythingLLM retweeted
Tim Carambat@tcarambat·Sep 30

The @AnythingLLM Android app went a year without updates. It was well due for a complete re-work. It's live now and it's amazing, token efficient, and practical. It won't compete for a private jet reservation. It won't get you banned from OpenTable. It just does what you want, right on your phone, without the infrastructure of a small nation. AI for the everyday. RAG, agentic search, reranking, doc gen and recurring tasks. Private, open-source, no vendor lock-in, use an SLM on-device or BYOK. Next up: one connected local-first experience across desktop, mobile and beyond. From desktop, to mobile, to more - all on your hardware and no vendor lock-in. anythingllm.com/mobile

1:17
AnythingLLM avatar
AnythingLLM@AnythingLLM·Sep 28

Almost every prompt requires web search. We are happy to announce our partnership with @youdotcom for AnythingLLM. Every user now will get accurate, fresh, and rich web-search with ZDR right out of the box. Server, Desktop, & Mobile. Read more: anythingllm.com/blog/you-com…

0:33
AnythingLLM avatar
AnythingLLM@AnythingLLM·Jul 7

AnythingLLM now ships with an OS-wide writing assistant called Magic Tab. Simply clicking on an input can make a contextual suggestion based on what you are looking at as well as contextual typeahead suggestions.

0:22
AnythingLLM avatar
AnythingLLM@AnythingLLM·Jul 6

"Intelligent Dictation" is live in @AnythingLLM. Now your local models clean up your words and paste them at your mouse cursor, but also can even see your open windows and give you better outputs based on what you're doing and what you said.

0:43
AnythingLLM avatar
AnythingLLM@AnythingLLM·Apr 1

Today, we demoed @PrismML's Bonsai 8B model in @AnythingLLM desktop to see if the 1-bit mode arch is the revolution local AI needs. Turns out, this is not an April fools joke. 1.1GB memory footprint for a whole 8B model with high accuracy

1:18
AnythingLLM avatar
AnythingLLM@AnythingLLM·20 Oct 2025

Over the weeked we passed by 50,000 GitHub stars on AnythingLLM! We are so lucky to have so many people inspired, using, forking, and contributing to our vision of an LLM agnostic tool suite you can run locally or for your organization. ⭐️ github.com/Mintplex-Labs/any…

0:10
AnythingLLM avatar
AnythingLLM@AnythingLLM·14 Oct 2025

If you have specific models, benchmarks, and other details you want us to try out, let me know, and we can publish those in a follow-up video. GA for these devices is published to be on Wednesday, Oct 15th, so you can let us try out your builds prior to get ideas.

AnythingLLM avatar
AnythingLLM@AnythingLLM·14 Oct 2025

We are a lucky partner to bench the new @NVIDIA DGX Spark before it came out. We build AI tools literally every day, so we were eager to get our hands on this to kick the tires.

Post attachment