Today, I want to highlight an incredible contribution from our community member in Discord, Nick Baker. He created a VS Code Extension that registers Agent Zero as a 'Language Model Provider'. It means he can open a native VS Code Chat and select 'Agent Zero' from the dropdown, just like you would select GPT or Claude and without the hassle of setting up the A2A protocol. This is a perfect example of extending the ecosystem.

If you're new to A0 and didn't know this was possible: yes, you can run it entirely for free! Agent Zero is now one of the most-used frameworks on the platform. 1.22B tokens processed this week. But the real win is that 215M of those tokens were on Grok 4.1 Fast, a completely free model. That means people are running AI agents for $0. No subscriptions, just Agent Zero + OpenRouter's free tier. [Agent Zero Setup Guide]: https://www.youtube.com/watch?v=w5v5Kjx51hs [OpenRouter Free Models list]: https://openrouter.ai/models/?q=free

That's half of my monthly Claude Max subscription I use for Claude Code. I am very satisfied with the results–built a helpful image generation content agent and Telegram bot interface for it–but I am appalled by how much it cost. Yes, I am spoiled by Claude Code. So I have 2 questions here on this topic: 1. Has anyone found a way to use Claude Code (in particular: your subscription to it) within A0? I have read of people "hacking" CC to use any model within it; this sounds like it would be somewhere in the same realm? Now that I'm done "building", I'm switching over A0's default model to Venice's google-gemma-3-27b-it so it'll just be using DIEM to run the recurring tasks... but damn, that's also horribly inconvenient to have to change the model like that all the time. Which leads to a second question: 2. Any plans for some kind of "model profiles" in the A0 interface so it's quicker to switch in & out of "building" and "automation" modes? Some kind of dropdown of frequently used models would also be helpful to speed things up. (BONUS QUESTION: Maybe there's a way to use A0 more efficiently to bring my Anthropic API calls down? Thanks for any tips)