Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Sidekick: Local-first native macOS LLM app

github.com

Post reply on HN
Print view View original

91–97 of 97 posts

Re: Sidekick: Local-first native macOS LLM app

#91

Post by brulard »

gcanyon wrote: post #87
brulard wrote: post #60

Earlier quoted context omitted.

Claude for Mac works quite well for me, and now with these MCP servers looking better than ever. And regarding electron - I have seen (and created for myself) awesome apps that would never existed without it.

What in your mind is the main advantage for using the app over the web site?

MCP servers work only on desktop app. Otherwise I don't mind using web app. On the desktop version I miss I can not have (at least i didn't figure it out) multiple conversations open at once. So I use web a lot.

Re: Sidekick: Local-first native macOS LLM app

#93

Post by angst_ridden »

Any idea how long Experts should take to import/index data? I pointed an expert at a big directory of source files on a M4 iMac with 32G RAM, and it pinned a CPU at 100% for 24 hours but was not finished.

A single file seems to finish quickly, but folders (even with just a few files) seem to be very slow.

Re: Sidekick: Local-first native macOS LLM app

#94

Post by derrasterpunkt »

pzo wrote: post #90
toomuchtodo wrote: post #84

Earlier quoted context omitted.

Any recommendations wrt resources that compare these or provides more context in that regard?

I haven't played with more advanced feature or RAG, but at least AnythingLLM seems to support both local and remote vector databases (you can choose: lancedb, chroma, pinecone, zilliz cloud), embedding provider again both local (ollama, lmstudio) and remote and adjust text splitting and chuncking. Have some Agent skills like Web Search, scraping websites, sql connector. Seems probably the most advanced and I like you…

When I remember correctly the non-docker install instructions were a bit buried on GitHub but Open WebUI runs fine in a venv.

Re: Sidekick: Local-first native macOS LLM app

#95

Post by abroadwin »

Terretta wrote: post #51
abroadwin wrote: post #44

Neat. It would be nice to provide an option to use an API endpoint without downloading an additional local model. I have several models downloaded via ollama and would prefer to use them without additional space being taken up by the default model.

From the README: Optionally, offload generation to speed up generation while extending the battery life of your MacBook. Screenshot shows example, mentions OpenAI and gpt-4o.

But it still forces you to download a local model before you can use that feature.

Re: Sidekick: Local-first native macOS LLM app

#96

Post by AutoAPI »

yohannparis wrote: post #30
AutoAPI wrote: post #3

An option to use a local LLM on network without needing to download the 2GB "default model" would be great

It's in the README https://github.com/johnbean393/Sidekick?tab=readme-ov-file#f...

It still forces you to download a model regardless
Post reply on HN