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)

You're building three different things, and your agent starts mixing up the context. It’s messy, and it breaks the flow. So, we fixed it. Meet Projects in Agent Zero. This is how we want to build, and we think you'll love it too.

It's here❗️ Projects are now in testing branch for you to try 🫵 👉 docker pull agent0ai/agent-zero:testing

I've got 3 variations of this conversation but this is always how it ends. I was impressed with Grok 4 Fast's 2M token context limit so I used a corporate/proprietary model for the first time with Agent Zero. I've never gotten a response like this from an open-source (Venice/Ollama) model when trying to change its behavior... what gives??