Auriga's technical report introduces a task-agnostic agent harness for zero-shot embodied manipulation, addressing the planning-execution gap it measured on RoboDojo, where removing arm execution raises GPT-6 Astra's success rate from 2. The report frames vision-language models as capable of interpreting instructions and planning manipulation tasks but struggling when acting directly as robot policies.
Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 2
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.