Hello everyone! We're looking for our community members who actively use Agent Zero to help us test Venice.ai models and share their experience. You would be given a free API key for the time necessary. This test will take as much time as necessary. We need about 10 people. Here's how it works: 1. Comment under this post that you're interested. 2. Venice API key will be sent to you in DM (unless we're full already). There's $25 daily limit on the key, feel free to use all of it. 3. See Venice.ai models available selection here: https://docs.venice.ai/overview/models 4. Test various models for chat, utility and browser in Agent Zero with Venice provider and your API key. 5. Comment and discuss here about your experience. How to test properly: - Create a set of testing tasks that the agent can do from start to finish - Change memory folder in settings before changing chat model (otherwise it can see previous solutions of other models) - Take notes of common errors, mistakes, hallucinations - Take speed and user experience into account - Browser agent is sensitive to model quality and breaks easily, browser needs to be tested for reliability frst Let's discuss the rest here, thank you all! 👍

Changelog: - Secrets management - agent can use credentials without seeing them - Agent can copy paste messages and files without rewriting them - LiteLLM global configuration field - Custom HTTP headers field for browser agent - Progressive web app support) - Extra model params support for JSON - Short IDs for files and memories to prevent LLM errors - Tunnel component frontend rework - Fix for timezone change bug - Notifications z-index fix

I just thought of a pretty cool idea and was hoping someone else would chime in? so the instruments folder is mainly for tools and also has the prompts. what if we create a custome robust prompt. like it could be a 20k token prompt for agent0 and that would get loaded at the beginning of the session for agent0 to have in his knowledge and not cost anything in tokens. Is this a good idea? I dont see any reason not to?

Tuesday, September 2nd @ 8:00 AM - 9:00 AM PST ( 3:00 PM UTC ) Our very own community members @Stirling Goetz , @Chris Johnson , and @Chris Theberge will present a deep dive into running local models specifically with Agent Zero, covering settings, software packages, loading, monitoring, and performance. It's going to be awesome! Click here and save the event to your calendar. Hope to see you there. 🔥

I think that @Stirling Goetz had mentioned that using deepwiki to chat about the code base for agent0 was one of the best ways to get questions answered. that is most definately a good way to understand any code base for the matter. just go to deepwiki.com search a git hub repo and start answering your questions. hopefully anyone reading this will discover that way to work is highly efficient. The more devs that work on the project the better it will become, just passing it forward and making this as a post so people can use this information.