DSH learning to hear · complete real trace · loops after episode 30 · click a dot for details · click empty space to zoom out · drag to scrub
pause · 0.5× 1× 2× 4×
an open instrument · est. 2026 · MIT
Proteus

Self-evolution for any agent harness.

Plug in. Evolve. Measure.
DSH evolution Enter the evolving lab Star on GitHub
↓
the specimen · DeepSeek Harness rc.8 — evolving its own first-class audio path
click a dot for its four-phase trace · click empty space to zoom out · drag to scrub · the replay loops
View report

The instrument

Any harness

Plug in DeepSeek Harness, Pi, our reference harnesses, or your own — one small adapter, upstream untouched. Each run can evolve its own harness source while the framework, sandbox, and measurement work unchanged.

Goal or no goal

Run evolution under one goal, many goals, or none at all — with evaluators the agent sees, or never sees. No-goal, unpressured evolution is a first-class mode.

Measured, not just scored

Structural distance per surface, behavioural distance with a permutation test, and a crystallization test: remove the injected preference and read back what the harness built on its own.

The evolve loop

EPISODE
context-fresh each episode · only files cross the boundary · print version

episode boundary: git snapshot · evaluators run · accept/reject — every run keeps its full history as a git repository

60-second demo · no key · no docker

git clone https://github.com/proteus-evolve/Proteus.git && cd Proteus
python3 -m pip install -e .
proteus run --harness minimal --arm neutral --arm review:notes --arm review:tools \
    --seeds 4 --episodes 8 --out runs/demo
proteus measure --harness minimal --out runs/demo