The self-improvement loop, run locally.

A Go port of SIA (Hebbar et al. 2026, arXiv:2605.27276): a meta-agent seeds a target agent, the target runs and records a trajectory, a feedback agent rewrites it for the next generation.

Research port. The orchestration loop, filesystem layout, and prompt builders are ported faithfully; the prompts are verified byte-identical against fixtures from the Python reference. Agent execution and evaluation sit behind Go interfaces, so the loop runs without a Python runtime.

What it does

Each generation runs the target agent, records its trajectory, and feeds that record to the feedback agent that prepares the next generation. Agent execution and evaluation remain Go interfaces. That keeps the orchestration independent of the Python reference and allows weights-mode output to feed local LoRA training in mlx-go-lm.