LM Studio serves. Haybox routes, verifies, accounts.
LM Studio’s local server slots in as a Haybox local tier. Keep its interface for tinkering; let Haybox decide which real work it should carry.
Three steps
Point LM Studio at the Haybox daemon and keep working. The exact configuration line for your version is in the docs.
- Install Haybox
One binary, Windows, macOS or Linux. It starts a local daemon and detects your hardware.
- Point LM Studio at the local endpoint
Start LM Studio’s local server. Haybox uses it as a local tier.
- Work normally
Nothing about your workflow changes. Watch the Ledger fill: a Waybill per task, and a savings report after thirty days.
Haybox is in private alpha, so step one is the waitlist for now.
What you get with LM Studio
- A shadow report built from your real traffic, not a simulation of someone else’s.
- Local-first routing with acceptance floors under it, so cheap only counts when it holds.
- A Waybill per task: the route, the cost per leg, what verified, and your decision.
- Rules that apply here too — the files you already keep are read natively.
The route, end to end. Illustrative.
Notes for LM Studio specifically
LM Studio’s local server slots in as a Haybox local tier. Keep its interface for tinkering; let Haybox decide which real coding tasks it should carry and show you, in the Ledger, how often that was the right call.
Questions
Is the GUI still usable?
Yes, entirely.
Which runtime should a new user pick?
Whichever you prefer; the Model Manager supports both, and the docs note current differences.
Claude Code · Cline · Local Model Manager · All integrations
See what your own traffic says.
Shadow Mode reports on the traffic you already have. Before that exists for you, the calculator will estimate it from your GPU and your monthly spend, and show you every assumption it used to get there.