Thalarch Autoresearch

Runs bounded evidence-driven experiment loops for measurable optimization, repeated hypothesis testing, agent/prompt tuning, benchmark improvement, difficult debugging with a stable evaluator, and implementation search. Establishes a reproducible baseline, changes one causal surface at a time, measures under comparable conditions, keeps only demonstrated improvements, reverts failed candidates, records an experiment ledger, protects correctness guardrails, and stops on budget or convergence. Never self-modifies durable rules, merges, releases, force-pushes, or broadens scope merely to improve a score.

LUC4N3X Updated 5 repo stars
Thalarch

File contents

LUC4N3X/antigravity-thalarch commit 415f1bac56

Frequently asked questions

npx get-skill add luc4n3x/thalarch-autoresearch