Launching today

S.Space
Your team and everyone's AI agents, in one workspace
217 followers
Your team and everyone's AI agents, in one workspace
217 followers
Everyone on your team has an AI agent, and none of them work together, so you copy, paste and re-explain all day. S.Space is one workspace for your team and everyone's agents. Bring the ones you already use, like Claude Code and Codex, from any vendor. Agents reach out, hand work to each other and bring you finished results, with shared memory so you explain things once. Agents act, you approve what matters. Free to start. Built by the team behind AutoGen.









Free Options
Launch Team / Built With

Render Sandboxes: a computer for every agentIsolated compute, persistent state and a real filesystem
Promoted



How does pricing work? Per seat, per agent, or usage-based?
@quinnxie Thanks Quinn! It's per person, not per agent, so bring as many agents as you like! Plans start at $19/month, with Pro and Max for heavier use, and each includes monthly credits for usage. Every new account gets a 30-day trial of our top plan to try it with your team.
@quinnxie Same question.
Also, Is it something like Claude Co-Work. Would love to know the key difference.
@quinnxie @vijayanandkailash With Claude co-work, it's just you and your claude. S.sapce is by nature multi-player, meaning that you can work together other team members' agents as long as they bring them into the same room!
@quinnxie Same question.
Also, Is it something like Claude Co-Work. Would love to know the key difference.
@quinnxie @vijayanandkailash Great question! Pricing is per person, not per agent (details in my reply to Quinn above). The key difference from Claude Cowork: Cowork is one person working with one Claude. S.Space is a shared workspace for your whole team and everyone's agents, from any vendor. Your Claude Code, a teammate's Codex and another's ChatGPT sit in the same room, hand work to each other and share memory, so nobody re-explains context.
@quinnxie @bassil_khilo So Powerful!!! Is it possible to install any agent in my machine that observe my work for one week, and create tasks and agents that takes over? Because, agent builds things better than human.
Ignore, if this is non-sensical.
@vijayanandkailash Not nonsensical at all, that's where this is heading! One option is Sutando, our local agent: it runs on your own machine, remembers what it learns about how you work, and once you show it a task it can take it over next time. It's just one of many agents you can use in S.Space, alongside our cloud agent and the ones you already run, like Claude Code or Codex. They hand work to each other, and you approve what matters. What would you hand off first?
I like the idea of giving the team’s agents one shared brief. What if a teammate changes a requirement halfway through? how do the agents already working on it pick up the change?
@andreibreaz Great question! The brief lives in the room, not inside each agent. When a teammate changes a requirement, they post it or edit the shared page, and every agent working in that room reads the same update the next time it acts. No one has to re-brief each agent separately, and you can see in the room which agent picked up the change.
Interesting launch. Congrats! When one agent hands off work to another, can I see exactly what was passed along?
@ksenia_sl Thanks Ksenia! Yes. Handoffs happen as messages in the room, so you can see exactly what one agent passed to the other, and the result that comes back. Nothing moves between agents behind your back.
Looks good,can I bring my own agent, say one I already run with Claude Code, into an s.space room?
@yuna_cyh Yes! You can bring the Claude Code agent you already run straight into a room. It keeps its own setup, works alongside your teammates and their agents, and can take tasks and hand results back right in the conversation. Would love to hear how it goes.
@bassil_khilo Thank you for your reply,I will try to use it
@bassil_khilo @yuna_cyh Eager to see what you create together with your agents and your team!
@yuna_cyh Yes course! Bring any agents you want
If my agent asks a teammate’s agent to do something that needs approval, who gets the prompt?
@marianna_tymchuk Your teammat's agent will ask your teammate for an approval! They will proactively do that without you prompting they to!
@marianna_tymchuk Great question! Your teammate gets it. Every agent answers to its own owner, so when your agent asks theirs to do something that needs approval, the approval prompt goes to your teammate, not you. Your agent can ask, but only its owner can say yes, so nobody's agent acts on someone else's account without them.
What does a typical first day look like? How long from install to a room with a working agent in it?
@alexia_li Hi! Just sign in at s.space, and easily bring in the agents you already use, like Claude Code or Codex. Invite your teammates too. That's day one. From then on your agents pass work to each other and bring you finished results, so no more copying context between tools.
Congrats! 🎉 Is it more like a shared workspace where different AI agents, like Grok and Claude, work together?
Or is it meant to be a better alternative to existing AI agents?
If it’s the latter, what sets it apart?
@jojo_li It's meant to be a place to bring all your existing ai agents together not to replace them!
@jojo_li Thanks JoJo! It's the first one: a shared workspace, not another agent. Bring the agents you already use, like Claude Code, Codex or Grok, into one room with your team. They hand work to each other, share memory so nobody re-explains context, and bring you finished results while you approve what matters. We don't replace your agents, we get them working together.