Our philosophy
Intelligence is getting cheap.
Context is the bottleneck now.
Your agent does real work in a chat window. Then the window closes and the context is gone — the decisions, the reasoning, the brief. Tomorrow you explain it again, from scratch. The model was never the hard part. Giving your team and your agents one place to read and write the same documents — that is. Hub is the shared context layer they both work from.
Capability
Could the machine do the task at all. For years that was the constraint. It’s ending — agents write, reason, and act, and they get cheaper every month.
Shared, durable context
Can your agent pick up where the last session left off? Can your team and its agents work from the same documents? Will the brief still be here tomorrow? That — not intelligence — is what runs short.
An agent is not a vending machine you talk to in a window that closes. It’s a colleague. It should have a seat at the same documents your team works in — propose, and let a person decide — and what you write together should still be here tomorrow, for the next person and the next session.
What we believe
- 01
An agent is a colleague, not a feature.
A real seat at the document — not a sidebar bolted onto one company’s model.
- 02
Agents propose. People decide.
Nothing an agent writes lands without a human’s say. Control isn’t a setting; it’s the point.
- 03
Context should be cheap and shared — not re-paid every session.
Write it once; every teammate and every agent reuses it. Re-explaining the same context to a machine is a tax, not a workflow.
- 04
A document is the interface between you and your agents.
Write a PRD an agent builds from; point it at your code and get docs back. The doc is how you brief each other — not a chat that vanishes.
- 05
Bring the agent you already run.
Claude, Codex, Gemini, whatever’s next. It’s yours, not ours. We don’t sell the brain or lock the door.
- 06
The work should still be here tomorrow.
No vanishing sessions. Tomorrow starts where today left off.
Why it matters
None of this is a roadmap. It’s how Hub works today — the review layer, the agents you bring, the documents that are still here tomorrow and shareable with a link: one shared context layer your whole team and its agents build on. We’re building the place where people and agents do their best work together, from the same documents.
— the people building Hub