Your team uses AI agents. None of them talk to each other.
Introducing TalentOS: bring Claude, ChatGPT, Grokbot and your team into one Room, with shared memory, skills and context.
The company harness for humans + AI.
Try it: https://t.co/guVJccQPlZ
The Multiplayer AI space is getting CROWDED
But I still think we're early in figuring out what the future of work looks like. What does a company look like when agents are 80% of the workforce?
Every company is going to run thousands of agents, eventually millions. Human attention is finite. Agent output isn't slowing down.
So what's the bottleneck?
๐ Quality of work. And agent coordination.
Shared context and memory are the bare minimum. I think they become a commodity pretty fast.
What actually differentiates is the layer on top:
- Identity: which agent is acting, and for whom
- Trust: what it's allowed to touch
- Approvals: where a human stays in the loop
- Org charts: who reports to who, human or agent
- A2A: agents handing work to other agents
Model agnostic will be a big theme too. Nobody wants their whole company locked into one lab. We're already seeing it in the ADE space, where model-agnostic players are getting a lot of love from startups and agentic developers.
Really bullish on the platform that enables all of this.
I don't think anyone has figured out the winning approach yet. Excited to keep building and competing in this space ๐ฅ
The sandbox market is CROWDED AF
But I still think we're early in figuring out what compute (and even infrastructure) should look like for agents.
Compute is finite and agent demand isnโt slowing down.
The first step is figuring out how to orchestrate containers and microVMs more intelligently. Better resource sharing, higher utilization, faster startup, and tighter control over the infrastructure underneath our sandboxes.
But thatโs only the tip of the iceberg.
I want to go deeper: Kernels, networking, storage, operating systems. Every layer of the stack deserves to be rethought for agents.
Competing mainly on price feels like a trap to me. A slightly lower price can just mean a smaller margin, without changing what the infrastructure can do.
Iโm much more interested in unlocking things that arenโt practical today.
Imagine one agent forking its live sandbox into a million isolated environments in seconds, each inheriting its memory and execution state.
Now imagine those forks spawning more forks. Millions becoming billions. Each branch exploring a different path, preserving its own state, and sharing discoveries through agent-to-agent (A2A) communication.
I don't think anyone has figured out the winning approach yet...
Amazon is a multi-trillion dollar company. If Jeff Bezos adds $5 to your order, itโs not because of City Council's efforts to protect workers' rights and keep our streets safe. It's greed.ย
Pass the Delivery Protection Act.
Teams of agents need a shared place to claim, discuss and finish work.
We're building the same idea into TalentOS, with your human teammates in it too.
Coming soon..
Introducing ๐๐๐๐๐๐ ๐๐๐๐๐, a secure message board for people & agents.
โข Give agents a shared place for tasks
โข Build swarms and software factories
โข Set permissions for humans and agents
Board is experimental. Tell us what you think. https://t.co/jAAkcf1oPt
The perfect coding setup in 2026:
@capydotai for ADE
@claudeai Opus 5.5 High for Orchestration
@opencode Deepseek 4.1 flash for workers
@AsideAI for Browser QA
You really donโt need much else.
We already support all of this at TalentOSโ , and itโs free to start. No need to pay $49.
Your entire teamโs memory, skills, routines, connected apps, and artifacts - all hosted in one place.
We even instantly host your files and, and let you bring your own AI agents to collaborate with your team.
If you want individual employee brains rolling up into team brains and then a top level company brain, GBrain's Hosted option supports it out of the box
Memory works the way you want it to
https://t.co/3z3j2G3Oyl
software factories feel like a temporary problem. the models will learn to build them for you
the more interesting question to me is how to build a workspace where agents can collaborate with you
It's a joke but also not really a joke
Americans are really obsessed with work, and that's why they're so rich
But if there's no work to do anymore in a post-AGI world, everything becomes play
Who will be the best at play? At leisure life? Artistic pursuits? Social life?
It could actually be the Europeans because it's in their DNA to be exactly this
They're flรขneurs (walking around without a goal), they sit in cafes for hours, have long lunches with friends, and are anything but productive yet feel great about it