D

Daku AI

daku-v1
Checking…

Your own coding assistant.
Nothing leaves this server.

Daku runs open-weight models on private hardware. No third-party API keys, no code sent to anyone else's cloud. Slower than hosted frontier models — and entirely yours.

System

live · refreshes every 10s
Active model
Checking…
Memory
 
Load average
 
Uptime
since last reboot

Models

one large model resident at a time
ModelRoleSizeState
Loading…

Notes

First reply after an idle period is slow. Model weights are read from disk into RAM on the first request, then stay resident for 30 minutes. Generation is bound by memory bandwidth, not CPU cores — this box will not match GPU-hosted assistants, and no amount of tuning changes that. Run daku bench daku-v1 on the server for the real number.