{"slug": "ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain", "title": "Ur-Agent-Team: a local-first hub where any AI agent can be the brain", "summary": "A developer released Ur-Agent-Team, an open-source, local-first agent hub that coordinates multiple AI agents on a single machine. The hub allows any connected agent to act as the system's brain, assigning tasks to other agents while keeping humans in control. Initial workflows include Codex, Claude Code, and Antigravity, with the goal of enabling easy integration for various local agents, CLI tools, IDE interfaces, and MCP-compatible tools.", "body_md": "I’ve made **Ur-Agent-Team** open-source today: [https://github.com/uncle-tyson/Ur-Agent-Team](https://github.com/uncle-tyson/Ur-Agent-Team)\n\nIt’s a local-based Agent Hub that coordinates AI agents operating on a single machine.\n\nThe core idea isn’t tied to any one vendor or integrated development environment. Any connected agent can act as the “brain” of the system, assigning tasks to other agents, receiving their responses, and continuing the workflow, with humans still in control of the process.\n\nCodex, Claude Code, and Antigravity are the first workflows I’ve been testing. But they’re just examples, not the ultimate goal of this project. The ultimate goal is to create a hub that’s easy for various tools to integrate with. This way, other local agents, CLI tools, IDE interfaces, and MCP-compatible tools can all work together within the same coordination framework.\n\nWhat it focuses on:\n\nWhy I built it:\n\nIn practice, real AI coding workflows already involve multiple agents working together. One tool might be best for handling command-line tasks, another for working within an IDE, and yet another for tasks like code review, research, or running long-running background processes. I wanted a simple, local system that allowed these various agents to cooperate with each other, without forcing everything to be handled through a single tool.\n\nThis is still alpha software, and its development was driven by real-world workflow challenges. The current adapters represent the tested solutions, and more hosts will require adapter support. But the core functionality of the software is now useful enough to be shared with others.\n\nIf you’re experimenting with local multi-agent coding workflows, I’d love to hear your feedback, any issues you encounter, or any PRs you might have.", "url": "https://wpnews.pro/news/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain", "canonical_source": "https://dev.to/gofyuen/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain-4ji1", "published_at": "2026-07-01 15:10:31+00:00", "updated_at": "2026-07-01 15:19:04.121865+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-infrastructure"], "entities": ["Ur-Agent-Team", "Codex", "Claude Code", "Antigravity", "MCP"], "alternates": {"html": "https://wpnews.pro/news/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain", "markdown": "https://wpnews.pro/news/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain.md", "text": "https://wpnews.pro/news/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain.txt", "jsonld": "https://wpnews.pro/news/ur-agent-team-a-local-first-hub-where-any-ai-agent-can-be-the-brain.jsonld"}}