AnythingLLM
AI
desktop ai assistant
SHOW HN2024
368points
77comments
#132of 3,515 in 2024
Top 4%of 2024 by points
How HN took it
CuriousMostly questions and neutral comments
13 positive, 22 neutral or asking, 2 mixed, 3 critical, out of 40 comments about the project. Thread score +0.25.
Design: 5 for, 0 againstIdea: 4 for, 0 againstExecution: 0 for, 2 againstDocs: 1 for, 0 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Easy setup and polished desktop install
From 3 comments
This definitely makes it super easy for less technical folks to access it ( got it up and running in less than 5 minutes ). Initial reaction is positive with just Ollama.…
A4ET8a8uTh0 on HNI have been really impressed with AnythingLLM as a no-fuss way to use LLMs locally and via APIs. For those of us who want to tinker, there's a solid range of choice for embedders…
phren0logy on HNI had a much smoother experience with the desktop version of AnythingLLM. There's more in openwebui, but the things that are in AnythingLLM are more polished (IMO).
phren0logy on HN
Supports many embedders, vector stores and providers
From 3 comments
this is super sweet for developers (or anyone else) who like to have granular control over their LLM set up - ability to edit system prompt - ability to change LLM temperature -…
md3911027514 on HNI have been really impressed with AnythingLLM as a no-fuss way to use LLMs locally and via APIs. For those of us who want to tinker, there's a solid range of choice for embedders…
phren0logy on HNYou can use LiteLLM _as the LLM provider_ which is just a relay to a ton of other models. For people who already have it set up connecting to x,y,z providers can keep that work…
tcarambat1010 on HN
Responsive maker and useful for enterprise deployment
From 1 comment
I’ve been attempting to deploy a customized AnythingLLM instance within an enterprise env. TimC (and presumably dev crew) are top notch and very responsive. Waiting for EntraID…
hm-nah on HN
Objections
Citations window shows garbled content
From 1 comment
Downloaded and checked it out. Looks great so far. Tried using it to read a bunch of regulatory PDFs using GPT-4o. Some quick and early feedback: 1. The citations seem to be a…
hannofcart on HN
Docker image pull timed out for one user
From 1 comment
$ docker pull mintplexlabs/anythingllm Using default tag: latest Error response from daemon: Get "https://registry-1.docker.io/v2/": net/http: request canceled while waiting for…
ranger_danger on HN
Unclear how privacy by default holds when cloud models are offered
From 1 comment
How do you ensure "privacy by default" if you are also providing cloud models?
vednig on HN
Requests
Search within existing chat history
From 1 comment
Downloaded and checked it out. Looks great so far. Tried using it to read a bunch of regulatory PDFs using GPT-4o. Some quick and early feedback: 1. The citations seem to be a…
hannofcart on HN
Keyboard shortcuts and desktop launcher
From 2 comments
This looks really great. Are you planning on adding shortcut keys anytime soon?
philipjoubert on HNWe actually are planning to really lean into the "Desktop assistant" style of things, so yes absolutely. Like how on Mac you can cmd+space to launch spotlight, we can offer the…
tcarambat1010 on HN
Custom CSS support
From 2 comments
What a coincidence, I just setup AnythingLLM yesterday for trying it on an enterprise level. I'm super impressed with most of the stuff I used so far. I just wish there was an…
fl_rn_st on HN+1 on custom CSS overwrites. A bigger feature that would add a lot of value might also be a prompt manager with a shareable prompt list.
db3d on HN
Home Assistant or Alexa integration
From 1 comment
Can this roll into home assistant and provide alexa at home in any capacity?
conception on HN
Questions
What hardware is needed to run it
From 2 comments
what kind of pc does it need ? ram, etc?
anonymous344 on HNDepends on the model you want to run! That is the beauty of it. If you can muster that ability to run a Q4 Llama3.1 8B - great, if your specs are really low end you can always…
tcarambat1010 on HN
How the hosted plan works and whether it has GPU access
From 1 comment
Question on the anythingllm hosted. So is the $50/mo just basically you are logging into some sort of Remote Desktop environment and run an anythingllm instance from there that…
indigodaddy on HN
How it differs from Open WebUI and Chatbox
From 2 comments
Have you tried openwebui? What are your thoughts on it vs this?
candiddevmike on HNHow does this differ from chatboxai? https://github.com/Bin-Huang/chatbox
santamex on HN
Alternatives named
Open WebUI
From 1 comment
Have you tried openwebui? What are your thoughts on it vs this?
candiddevmike on HN
Chatbox
From 2 comments
How does this differ from chatboxai? https://github.com/Bin-Huang/chatbox
santamex on HNChatboxai is a client for multiple AIs like OpenAi, Cloude, etc. It does not work on your local files and documents.
Ringz on HN
Ollama
From 1 comment
This definitely makes it super easy for less technical folks to access it ( got it up and running in less than 5 minutes ). Initial reaction is positive with just Ollama.…
A4ET8a8uTh0 on HN