Working Memory
Memory quiet
—%
OpenCortex
llama.cpp · local
Conversation
Live local chat
↵ SEND · SHIFT + ↵ NEW LINE
Runtime Observatory
Qwen2.5 1.5B · Q4_K_M
IDLE
READY
Context Window
Context resting
0/ —
→
Token Stream
Stream dormant
0.0tok/s
Engine State
Engine healthy
—ms
Cortex Core
Ready for input
ENGINE IDLE · SLOT AVAILABLE
Measured live by llama.cpp
Prompt eval
measuring
KV evidence
unavailable