LibreChat

GitHub links: - https://github.com/janhq/jan - https://github.com/danny-avila/LibreChat - https://github.com/Mintplex-Labs/anything-llm

Given how much data (personal and otherwise) that you're likely going to feeding into it, I would HIGHLY recommend using an open-source chat interface like Jan. It's cross platform, works with most LLMs, and has extension support. https://github.com/janhq/jan Another alternative is LibreChat, it's more fully featured but its heavier weight and spins up quite a few docker instances. https://github.com/danny-avila/LibreChat If you're going through the trouble of running models locally, it doesn't make sense to couple that with a proprietary closed source interface (like LM Studio).

Just a reminder that LibreChat exists. It's FOSS, and lets you bring your own APIs key for all the LLM providers. The UI is excellent. You can run it locally, or as I do on a $5/month Linode server. I don't want to pay ~20/month for each LLM provider, so I put $5 to $10 on my Anthropic and OpenAI API accounts every couple months, and that lasts me plenty long. You get to save all your chats, change models mid-chat, view code artifacts, create presets, and much more. If you don't know how to set up something like this, ask ChatGPT or Claude. They will walk you through it, and you will learn a useful skill. It's shockingly easy. https://librechat.ai https://github.com/danny-avila/LibreChat

As far as open source goes, I'd probably recommend LibreChat. It has connections for ollama, openai, anthropic, etc. It let's you setup auth so you can theoretically use it from anywhere (phone, etc.). Fair warning, it's relatively heavyweight in so far as it has to spin up a number of docker instances but works very well. https://github.com/danny-avila/LibreChat

Since you're using the API, any particular reason why you didn't just use Librechat? It already has support for API keys for Claude, OpenAI, and you can also use it with locally hosted LLMs through Ollama, and has all of the same feature (saved conversations, file attachments, caching, etc.) https://github.com/danny-avila/LibreChat

Not to add more to the mix, but I've been very happy with Librechat: https://github.com/danny-avila/LibreChat

I'm looking to provide our 4-person team access to various LLMs, including OpenAI, Anthropic, Meta's Llama, and some others. I want to have browser-based UI (like ChatGPT) to upload files, get Markdown-reponses and have price control to avoid unexpected high costs at the end of the month. My current plan is to purchase API keys from different LLM providers and use LiteLLM as a proxy to setup cost limits OR to use OpenRouter.ai (potentially still using LiteLLM). LibreChat currently doesn't support "passing through" uploads, but this feature is expected to be implemented this week: https://github.com/danny-avila/LibreChat/discussions/3760#discussioncomment-10445600 My Questions: 1. Is my approach using LiteLLM or OpenRouter with a UI a viable solution? I believe this could be more cost-effective than purchasing monthly chat accounts for eac

A better question would be over something like Jan or LibreChat. Ollama's is CLI/API/backend for easily downloading and running models. https://github.com/janhq/jan https://github.com/danny-avila/LibreChat Jan's probably the closest thing to a open-source LLM chat interface that is relatively easy to get started with. I personally prefer Librechat (which supports integration with image generation) but it does have to spin up some docker stuff and that can make it a bit more complicated.

Pretty much all of the features you mention are already in LibreChat (MIT License). If you don't mind self-hosting, then it has branching, convo search, change models mid-chat, "presets" (save system prompts), and a whole lot more. I've deployed it in my gov agency for months now, and I've had amazing feedback. https://github.com/danny-avila/LibreChat

https://github.com/danny-avila/LibreChat I've been using LibreChat which has all of those features and more. Self hosted, MIT license, and auth built-in.

The author of LibreChat [0] teaserd on discord that he's working on one. LibreChat is already the best "chatgpt ui" clone I could find (it has some rough edges, but not as many as the official chatgpt ui). [0] https://github.com/danny-avila/librechat Was also recently discussed here https://news.ycombinator.com/item?id=38502805

Good to know, thanks! I still find it a bit concerning that even the LibreChat docs about LiteLLM don't mention local models in the list of use cases. It looks like there's a GitHub ticket to add that to the docs [0], which would be good. Maybe I'm just growing old and crotchety, but it makes me uncomfortable to see a word like Libre—which was specifically coined in English to differentiate itself from Free-as-in-Beer—used in a context where monetary cost seems to be the primary concern in the maintainers' minds. [0] https://github.com/danny-avila/LibreChat/issues/1131