Hey everyone, We posted a video showing how to integrate APIs into Agent Zero on the fly. Beyond just reading the docs, notice how the agent delivers the result? We instructed it to use the notify_user tool with HTML tags. This turns Agent Zero into a real-time dashboard for any tool you connect. 1. Upload Docs of any API. 2. Set Secrets globally or in your Project Secrets. 3. Enjoy your new integration. The new sleek UI is a work in progress available in the development branch of our GitHub. Watch the full workflow.

I asked A0 to install n8n within it's system and allow me to view it. It installs and you can view n8n via a secord port and browser tab or window (had to enable 2 ports via docker desktop, agent guided me through "make sure you backup first"). Uploaded the n8n documentation to it, gave it access to the perplexity, deepwiki, and Ref mcp servers. Now I'm able to run n8n inside A0. I have only provided pre-built workflows at the moment. I had A0 create an n8n agent, and workflows folder that it saves each workflow along with its purpose to it and reads from. I just drop the .json into the chat. It pulls up the workflows in the n8n instance and runs them, it even debugged one workflow for me spot on. Going to test and see how it does building workflows from scratch. Best part is that I am currently using the free xiaomi flash model via openrouter and so far it works flawlessly. I imagine that using claude opus or sonnet would make it even more powerful. Just something to test out if anyone uses n8n regularly. Now you can do it all via A0. So far so good.

Hey Guys, I just joined the group, do you have any ideas about how to run this with LM Studio with LLM model locally set on the Mac

🆕 Release! v0.9.2 - Kokoro! 🥳 Agent Zero can now talk to you like a human. ⬇️ docker pull agent0ai/agent-zero