AI Chat

What is this page?

This page goes into more detail about what each of the AI chat services on https://kek.ms/ are, and also technical details.

What is LibreChat?

This is my preferred frontend for interacting with LLMs. It's very well featured, doesn't slow down your PC with long chats, and is extensible. It's connected to my llama.cpp servers - which run the actual models. You can sign up with a fake email if you want.

How to select model in LibreChat

Ignore the OpenAI, Anthropic, etc menus. You only care about the "My Agents" and "Keks AI" menus.

You can select the model here and configure it yourself: https://kek.ms/static/screenshots/screenshot_20260909_225353.png

I use these settings: https://kek.ms/static/screenshots/screenshot_20260909_225717.png (You can make a preset)

Or you can import this preset which has things set up for you: https://kek.ms/static/chat_preset.json - I recommend doing this

Or you can use the pre-configured agent, which has tools like web search already enabled here: https://kek.ms/static/screenshots/screenshot_20260913_024153.png - it's good but I noticed it has some delay for each prompt where it reprocesses the whole thing for some reason

What is llama.cpp?

You don't really need to know this but it's here for clarity - this is what runs the actual models so that LibreChat can use them. It's the backend. It also does however serve its own little frontend. This is what the "no sign up required" links are.

Why use LibreChat instead of the "no sign up required" links on the same page?

The ones where you don't need to sign up do not store your chats on the server. This means chats etc are stored only in your browser. This is advantageous from a privacy perspective - but it means if you reset your browser, you lose your chats. LibreChat stores chats on the server, tied to your account. LibreChat also lags less with long contexts and is overall better to use. The no-sign-up-required links are just the default web interface which llama.cpp (the backend) provides. You can also input memories which persist per conversation and stuff like that.

However, if you do want to use the no-sign-up ones, you can actually export your chats from there and import them to other browsers if you want. It's good for one-off tasks.

What if I want to use my own frontend?

You can use the models in any OpenAI compatible frontend or tools. The endpoint URL is "https://llama.kek.ms/v1/" or "https://llama.kek.ms/v1/chat/completions" and you can use this in OpenCode, or Codex, or whatever.

What model is running?

I run this...

https://huggingface.co/HauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF

I run it at 8-bit quantization across four GPUs.

I keep thinking mode off by default, because I don't find it particularly useful. I'd rather have a back and forth to reach the desired outcome instead of the model having a chain of thought. If you want it to do a chain-of-thought you can just ask it to do so. Do this by explicitly telling it "You must output a chain-of-thought before outputting your response".

I keep it online 24/7 and just use it as needed. I keep it at 262,144 maximum tokens context.

I don't use any MCP tools like web search since I'd rather do it myself. You can add your own MCP tools if you want though.

Limitations, and how to overcome them

The model knowledge cutoff date is late 2024. That means it has no new information beyond that date.

So you need to use the MCP server in LibreChat to get access to the web if that's something you need.

Alternatively, you can connect it to your own MCP servers to give it tools to use, some examples here.

https://mcpservers.org/