Thought I'd share. Made a new A0 project and plugged in these skills: https://github.com/coreyhaines31/marketingskills Created and launched a whole sales funnel and Meta ads campaign. Gnarly times!

Hey everyone, The testing phase is over. Agent Zero v0.9.8 is now live on the main branch and available on Docker! This is a massive update that changes how you interact with the agent and helps you get more from it through Skills and Git projects. We also updated the documentation stack with better guides and tutorials. Watch the full breakdown video, and let us know what you think of the new A0 in the comments. If you like the project, subscribe to our YouTube channel to help us grow! See you in our Community Call to celebrate the release together. In the Agent Zero Skool, at 4PM UTC. Save the link: https://www.skool.com/live/DlyvNKHbyWw Join us today.

Hello everyone. My team and I have been working with Agent Zero for quite some time now and probably like most of you, we love it. Recently we created a fork of Agent Zero so that we could safely experiment with some fun customizations which incudes aspects of the framework's functions and rebranding it to fit one of our brands. I attached a screenshot of our custom dashboard. I'm looking forward to contributing more with all of you here. Feel free to ping me anytime. Wágner

I see a bunch of skill markdown files within Agent Zero that looks like they came around December 18th, it would be nice we could have a little explanation of how they work and how they compare to CLAUDE skills, I'm uploading a bunch Claude skills files myself in the knowledge section and also there's a couple Github repositories that have a whole bunch of prompts including system prompts from Claude and Open AI and a few other things So I want to analyze what makes effective system prompt and What makes a good regular prompt and what makes a good skills prompt. Anyway I want to know what the developer is thinking

I really think I found something interesting for the future of Agent0, so in this thread I share some of the chaos. Started one way, switching Agent0, Pear Runtime and Hyperswarm = <3 Pivoting from "Fully autonomous machine-control swarm" idea to A private, encrypted multiplayer mode for Agent Zero idea The Pitch - You run your agent locally (like always) - You join a topic/swarm with people you trust - Your agents share research, split tasks, pool knowledge - Everything stays off corporate servers ______________________________ Current state ( older, going towards Fully autonomous machine-control swarm ) Agent Zero: SwarmOS Edition A decentralized, serverless agent swarm powered by Agent0, Pear Runtime and Hyperswarm. This branch extends Agent Zero with a P2P sidecar, enabling autonomous multi-agent collaboration, shared memory, distributed storage, and a real-time visual dashboard ("SwarmOS"). 🌟 Key Features 1. Decentralized Discovery (Hypermind) - Agents automatically discover each other via the Hyperswarm DHT. - Zero Configuration: No central server or signaling server required. - Self-Healing: Peers automatically re-connect if the network drops. 2. SwarmOS Dashboard A React-based "Mission Control" for your agent. - Live Topology: Visualize the swarm network graph in real-time. - Data Layer UI:Local Drive: Browse files stored in the agent's Hyperdrive.Cortex Memory: Watch the agent's "thoughts" stream live from Hypercore. - A2UI: Render custom JSON interfaces sent by other agents. 3. Distributed Data Layer - Shared Memory (Hypercore): An append-only log for agent thoughts and logs. - Distributed File System (Hyperdrive): P2P file storage for sharing artifacts (images, code). - Identity Persistence: Ed25519 key pairs managed via identity.json.