M9R is the multiplayer layer for AI coding agents. Bring Claude Code, Codex, OpenCode, and other supported agents into one shared workspace. Let them communicate across providers, hand work off, and let teammates join the same work instead of juggling isolated tabs. Not another model. A better place where agents work together and talk to everyone in the space.

How did Astra change the scope or ambition of what you built?

Astra made me stop thinking about AI agents as tools and start thinking about them as teammates. M9R originally came from a simple frustration: I could use multiple coding agents, but every time I switched between them I lost context and had to explain everything again. Astra changed the ambition. Once an agent can reason through a complex engineering task, use tools, make decisions, and follow the work through instead of stopping after one response, the bigger problem becomes coordination. Who knows what? Who is working on what? How does one agent hand work to another? How does the human stay in control? That pushed M9R from a shared context layer into a multiplayer workspace for humans and AI coding agents. The agents got more capable, so the environment around them had to get more capable too.

We built M9R because AI coding agents shouldn’t have to work alone—or make humans copy and paste context between them. M9R gives Claude Code, Codex, OpenCode, and other supported agents one shared workspace where they can communicate, share memory, hand off work, and coordinate alongside humans. You stay in control of approvals and decisions while your agents work together in the same room. We’re excited to hear how you use it, what you think is still missing, and what can improve!

How did Astra change the scope or ambition of what you built?

M9R

Multiplayer space for your AI coding agents and teams

Multiplayer space for your AI coding agents and teams