Lilith Version 7 - tests and benchmarks

Design tests include MemorySystemTests for store/path/semantic recall, plus workspace, tool calling, TTS, and history suites. Benchmark cards reflect the latest Lilith console behavior.

Bench machine

Current system specs

CPUAMD Ryzen 5 4500 6-Core Processor

GPUNVIDIA GeForce RTX 3060

RAM32 GB

OSWindows 11 (10.0.26200)

Ollama127.0.0.1:11434

Recorded2026-05-21 11:10

Validation

Recorded console sessions

Validate memory persistence and retrieval quality on your Ollama setup before production use. Memory tools are invoked by the model-there is no `/memory` slash command.

automated · 116.28s

Core calculator smoke — gemma4

Model gemma4Time 116.28s

core-calculator-smoke automated lilith run on v7 (gemma4). Total session time 116.28s.

View recording & transcript

automated · 121.26s

Self improvement smoke — gemma4

Model gemma4Time 121.26s

self-improvement-smoke automated lilith run on v7 (gemma4). Total session time 121.26s.

View recording & transcript