# [How C3] Leo - Brave Browser Assistant

Leo is an AI assistant that is integrated into [Brave Browser](https://brave.com/) which in simple terms is an improved version of Google Chrome as it built on the same engine. Once downloaded and installed we can get started with the assistant setup.

## Connect your comput3 account

Paste [brave://settings/leo-ai](brave://settings/leo-ai) into the address bar of your brave browser or navigate via menu > settings > leo to get to the page. Scroll down and click "Add new model" to connect the llms from your comput3 account.

[<img src="https://hackmd.io/_uploads/Hkuh70QBll.png"/>](https://hackmd.io/_uploads/Hkuh70QBll.png)

We're going to connect Llama3.3 with full context support.

- Label: Llama 3.3 70b
- Model request name: llama3:70b
- Server endpoint: https://api.comput3.ai/v1/chat/completions
- Context Size: 131072
- API Key: your-comput3-api-key (scroll to the end of this post to find it)

Click Add model to finish this step.

[<img src="https://hackmd.io/_uploads/rkU2B07Bgg.png"/>](https://hackmd.io/_uploads/rkU2B07Bgg.png)

Before leaving the settings select your newly added model as the default to ensure that Leo always utilizes your powerful 70b model instead of those 8-14B models.

[<img src="https://hackmd.io/_uploads/Hkc18A7Hgg.png"/>](https://hackmd.io/_uploads/Hkc18A7Hgg.png)

## Start Talking to your assistant

Whenever you are browsing via Brave you can now hit ctrl+B to open Leo. The first time you hit that shortcut it might lead you to the bookmarks or your browser history. Just click the Leo icon (looks like a star) on top of the sidebar list to switch to Leo view. The next time you hit ctrl+B you'll be greeted by your AI assistant.

[<img src="https://hackmd.io/_uploads/ByrDk1ESlg.png"/>](https://hackmd.io/_uploads/ByrDk1ESlg.png)

[<img src="https://hackmd.io/_uploads/rJLnk14Bex.png"/>](https://hackmd.io/_uploads/rJLnk14Bex.png)

# Setup your comput3 Account

After you've [acquired](https://dexscreener.com/solana/34qhkhrhyningwruftqjnb2vfv8oqyqd5tvdwwde1man) and [staked](https://app.streamflow.finance/staking/solana/mainnet/DGZebyog1twdFaKwN2KZkBLxDkzX4rh7L61S6TAty8et) some $com token you can [login to your dashboard](https://launch.comput3.ai/) with your solana wallet and grab your API key at the bottom page. You can do way more things in this dashboard like spin up comfyui instances or launch dedicated ollama instances with broader model selection but for standard 70b llm inference via the default comput3 base url (https://api.comput3.ai/v1) this is not needed. In this tutorial we keep it simple.

[<img src="https://hackmd.io/_uploads/BJGO16mreg.png"/>](https://hackmd.io/_uploads/BJGO16mreg.png)

If you run into issues join the [official comput3 Discord server](https://discord.gg/EFZPGm9qUu) and ask the community.