Every slice has its own everything
thinslice binds each git worktree to its own bag of state — no shared databases, no shared ports, no shared config. Corust runs inside a slice and can't reach yours.
One command to launch
Spin up a fresh Rust worktree with cloned state and hand it to Corust in one shot. thinslice handles the postgres clone, the redis snapshot, and the port reservation — you just describe the task.
Isolated worktree
with
Cloned state
Review, preview, ship
When Corust is done, review the diff inline, run your app against the isolated database, then commit and open a PR — without ever touching your main working tree.
Forget about ports
When Corust sessions run in parallel, each slice gets its own reserved port range. No conflicts, no guessing which process is on which port.
Fully scriptable
Everything you can do interactively, you can do from a script or CI pipeline.
slice tmp --from current -- claude -p "implement user authentication"slice tmp --from current --name feature-x -- claude -p "implement feature X"slice ls # list running slicesslice status feature-x # check a sliceslice rm feature-x # tear down + clean state
FAQ
+What credentials does Corust need?
+Is this free?
+Does my code or data leave my machine?
+What does "state" mean exactly?
+Do I need Docker or Kubernetes?
+What happens when I'm done with a session?
+Can I run multiple Corust sessions at once?
+Do I need git?
+How does the Postgres clone work?
thinslice gives every coding agent its own isolated slice of your stack. No Docker, no VMs, no shared databases. Agents work in parallel without stepping on each other.
If thinslice has been useful and you want to say thanks, or if you just want to talk shop about agents, evals, sandboxes, or go-to-market for automation products, give me a call.