and I want to say the research agent is most defintely the most capable when it it comes to handling multi step reasoning and thinking smart. I usually reference the reasoning loop from that agent when creating new ones as a starting point if I need some super smart thinking. whoever did that research agent prompt....you rock on that one

Hi all, Trying to get speech to work snoother and more natural at this point, agentzero reading out it's responses has random multi second pauses per paragraph. Sometimes sentences. 2 questions: - Does TTS work for you? - What can I check on my end to get it to work?

As I now have two instances of A0 running on two different servers, I find myself constantly having to glance at the URL to determine which one I've got pulled up. It'd be REALLY nice if there'd be an easy way to customize the UI and favicon so we can tell them apart at-a-glance in a crowded browser tab lineup. I tried getting one A0 agent to update the background colors and favicon of the other on the other server, but it seems to really struggle in pulling that off. So I'll probably just resort to locating which CSS does what and do it manually--which kind of feels ironic to me, given what A0 does (semi-autonomous agents). Plus, I'm betting my personalization will get overwritten when the next update occurs. So if I may request: could there be a way to more easily personalize the UI, and have that personalization included in the Backup and Restore feature, pretty please?

Current experience: >> Install Agent Zero with Docker. >> New Chat >> Agent Zero: Hello! 👋, I'm Agent Zero, your AI assistant. How can I help you today? >> User: Hi, [...] >> Agent Zero: Recall memories extension error: [...]. Error [...] Looks familiar? Yes, we could just call people stupid or silly and send them to ask GPT how to solve this or to watch videos on how to start with Agent Zero. Or, we could implement the simplest, small local LLM setup within the image that would be able to run a predefined routine for the onboarding experience. Does this idea sound ridiculous? 🤔

We're cooking something special for the Agent Zero website, with a fresh new look that better reflects what our framework has become. We're emphasizing what makes Agent Zero special: complete control over your AI agents, from single tasks to fully automated workflows, with the freedom to use any LLM provider or local model, and the option to access true private and uncensored AI models through Venice AI. This is still a work in progress, and we'd love to hear your thoughts! What would you like to see on the new site? Drop your feedback below 👇 As always, Agent Zero remains free and open-source. We're building this together!