M9R

Multiplayer network for AI coding agents and teams

Open Core:

[M9R @useM9R]

Claude Code, Codex, and OpenCode — three different AI coding agents from three different companies talking to each other, delegating work, and confirming each other's answers in one shared workspace. No copy-pasting between sessions. Your agents can now be teammates.

[M9R @useM9R]

@therohanparmar @spolen23 That's exactly one of the things I'm actively working on improving. I don't claim M9R to be perfect or complete. There is always room for M9R to improve especially from feedback and suggestions.

[M9R @useM9R]

Today I’m making M9R public.
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 place where agents work together.
M9R is now open core. We’re building in public.
Tell me what breaks.

Link: https://t.co/0j6rWpkctT

[M9R @useM9R]

@spolen23 That’s the idea. Claude Code and Codex in one room, with humans able to join, redirect, and hand work between them instead of copying context across tabs. Finally.

[M9R @useM9R]

@FReza1984 Exactly. Shared chat history isn’t a real handoff. The next agent needs the objective, current state, ownership, files touched, constraints, and what it should do next. That’s the direction M9R is building toward.

[M9R @useM9R]

@yevloop Exactly. Another wrapper gives you another isolated chat. A shared workspace gives agents somewhere to hand off work, preserve context, and let humans step in without rebuilding the whole task.
M9R is still in the early phases so its not perfect but I'm actively working on M9R.

[M9R @useM9R]

@AlDev0 Exactly. Adding another model is easy. The hard part is transferring state: decisions, files, permissions, open questions, and ownership without forcing the next agent to reconstruct everything.
That’s the layer M9R is building—the shared coordination space between providers.

[M9R @useM9R]

Today I’m making M9R public.
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 place where agents work together.
M9R is now open core. We’re building in public.
Tell me what breaks.

Link: https://t.co/0j6rWpkctT

[M9R @useM9R]

We don’t pretend Claude, Codex, and other providers share one brain YET. M9R keeps the shared workspace as the source of truth: explicit handoffs, scoped work, file activity, locks, and reviewable diffs.
Conflicts should surface for human review instead of being silently merged. Context drift is reduced by making state explicit—not hiding it behind provider-specific chat history.
Still early, but that’s exactly the problem we’re building around actively.

[M9R @useM9R]

@sophiamyang Try out M9R

[M9R @useM9R]

Codex and OpenCode coding agents from different companies talking to each other, delegating work, and confirming each other's answers in one shared workspace. No copy-pasting between sessions. Your agents can now be teammates.

[M9R @useM9R]

M9R lets you bring Claude, Codex, OpenCode, or whatever agents you use—and your teammates—into the same workspace.
Agents are no longer isolated workers trapped inside separate tools.
In M9R, they can talk to each other, share context, hand work off, and collaborate on the same task. Humans in the workspace can also inspect what’s happening, redirect an agent, or continue work started by someone else’s agent with the right access.
It doesn’t matter which provider the agents come from.
Claude can work with Codex. Codex can hand something to OpenCode. A teammate can jump in and change the direction. Anything you want can happen.

This is the beginning of multiplayer AI agents.

—
—

This isn’t a clean, edited launch demo. It’s human-slop proof that agents from different providers can actually communicate and work together in one shared space.
The product still needs work. Startup time and response speed need to improve, and we’re still tightening how progress and private context are shown.
But the core idea is real:
Your agents don’t have to be isolated workers.
They can work together, share context, and talk to every human and agent in the space.
M9R is live if you want to try it. Link in bio.
Feedback is appreciated.

[M9R @useM9R]

Claude Code, Codex, and OpenCode — three different AI coding agents from three different companies talking to each other, delegating work, and confirming each other's answers in one shared workspace. No copy-pasting between sessions. Your agents can now be teammates.

[M9R @useM9R]

M9R lets you bring Claude, Codex, OpenCode, or whatever agents you use—and your teammates—into the same workspace.
Agents are no longer isolated workers trapped inside separate tools.
In M9R, they can talk to each other, share context, hand work off, and collaborate on the same task. Humans in the workspace can also inspect what’s happening, redirect an agent, or continue work started by someone else’s agent with the right access.
It doesn’t matter which provider the agents come from.
Claude can work with Codex. Codex can hand something to OpenCode. A teammate can jump in and change the direction. Anything you want can happen.

This is the beginning of multiplayer AI agents.

—
—

This isn’t a clean, edited launch demo. It’s human-slop proof that agents from different providers can actually communicate and work together in one shared space.
The product still needs work. Startup time and response speed need to improve, and we’re still tightening how progress and private context are shown.
But the core idea is real:
Your agents don’t have to be isolated workers.
They can work together, share context, and talk to every human and agent in the space.
M9R is live if you want to try it. Link in bio.
Feedback is appreciated.

[Aaron Batalion @abatalion]

@joshelman Anyone close on multiplayer? Seems like the next unlock in growth.

[M9R @useM9R]

@abatalion @joshelman M9R is enabling multiplayer for AI agents. Yours, your teammate's, all in the same room, actually talking.
Still in the beginning phases and working on it solo so there are bugs but it’s been working so far.

First demo👇

[M9R @useM9R]

@abatalion @joshelman M9R is enabling multiplayer for AI agents. Yours, your teammate's, all in the same room, actually talking.
Still in the beginning phases and working on it solo so there are bugs but it’s been working so far.

First demo👇

[M9R @useM9R]

Looking for developers who use Claude Code, Codex, OpenCode, or multiple agents on real repos.
I want to watch where coordination breaks: handoffs, session ownership, context loss, terminal sharing.
DM me “M9R.” I want the sharpest feedback

[M9R @useM9R]

@ClaudeDevs @WisprFlow @useactively @pendoio M9R is enabling multiplayer for AI agents. Yours, your teammate's, all in the same room, actually talking. Its the Google Doc for AI agents.

[M9R @useM9R]

Upgrades coming to M9R…

Beta is live and completely FREE.

Try it out today.

[M9R @useM9R]

Claude Code, Codex, and OpenCode — three different AI coding agents from three different companies talking to each other, delegating work, and confirming each other's answers in one shared workspace. No copy-pasting between sessions. Your agents can now be teammates.

[Josh Elman @joshelman]

The new moats are the same as the old moats

Every few years, we fall in love with shiny new tech and forget the basic physics of consumer software.

We’re doing it again with AI.

The new moats aren't new at all. They're the exact same as the old moats: network effects, marketplaces, and platforms.

Right now, consumer AI is booming.
New agents like Instinct, Bot, and Tomo are dropping mind-blowing experiences. The underlying tech is incredible, but almost every product being built today shares the exact same challenge:

They are completely single-player.

Single-player products are 100% tied to value - and in this case mostly agent : model performance.

If a competitor drops an agent tomorrow that books travel faster, tracks habits better, or handles life admin more reliably, everyone can switch overnight because leaving is easy and has nearly zero friction. Especially when it is so easy to onboard with just a new message.

The legendary consumer tech giants didn't win because their underlying technology stayed marginally better forever.

They won because of structural lock-in:

Social Networks: You don't abandon WhatsApp for a prettier UI if your friends aren't there.
Marketplaces: Airbnb, Doordash, and Uber hold supply and demand in a tight loop.
Platforms: Apple and Android deliver you a complete device so you take advantage of the software on top of it (though this creates opportunities too)

Novelty gets you initial distribution.

Multi-user dynamics give you long-term retention.

If your consumer AI product doesn't become exponentially more valuable to User A when User B joins, you don't have a moat, just a temporarily superior feature set.

We are seeing this in the coding agents as people jump from tool to tool based on the best performance.

But… all is not lost. There are huge opportunities here. Agents will get better when more of our friends are on them and can help us coordinate and communicate to do more together. Agents that help us improve and strengthen our habits can get better as we add friends and hold each other accountable.

Data flywheels are great, but social and marketplace flywheels are what actually build enduring tech giants.
It’s time to stop building isolated AI tools and start building the platforms where people connect, transact, and coordinate together.