You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
One thing I still find surprisingly painful is working across multiple machines.
I have an always-on Mac mini and a couple of laptops. They mostly have the same repos and tooling, but from an agent perspective they’re still separate worlds: sessions and useful state tend to stay wherever they started.
I know #5363 / #5544 are tackling thread handoff, but I wonder if there’s a broader opportunity here: could T3 treat equivalent environments as execution targets for the same logical workspace?
Not by syncing credentials, binaries, MCPs, etc. blindly — machines will always differ. More at the T3 layer: repo/project identity, threads, relevant state/preferences, and generally making switching machines boring.
A lot of the pieces seem to already exist. T3 feels like a pretty natural place to solve this.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
One thing I still find surprisingly painful is working across multiple machines.
I have an always-on Mac mini and a couple of laptops. They mostly have the same repos and tooling, but from an agent perspective they’re still separate worlds: sessions and useful state tend to stay wherever they started.
I know #5363 / #5544 are tackling thread handoff, but I wonder if there’s a broader opportunity here: could T3 treat equivalent environments as execution targets for the same logical workspace?
Not by syncing credentials, binaries, MCPs, etc. blindly — machines will always differ. More at the T3 layer: repo/project identity, threads, relevant state/preferences, and generally making switching machines boring.
A lot of the pieces seem to already exist. T3 feels like a pretty natural place to solve this.
All reactions