Crayotter: Traceable Multi-Agent Workflows for Long-Form Video Editing
For video editors and AI researchers, Crayotter addresses the challenge of maintaining narrative intent and diagnosing failures in automated long-form video editing.
Crayotter introduces a traceable multi-agent system for long-form video editing that externalizes inspectable artifacts, enabling selective revision of failed segments. In human evaluation on 23 editing themes, it achieves an average score of 3.40/5, outperforming baselines CapCut-Mate (2.44) and CutClaw (1.70).
Editing a long-form video from heterogeneous footage requires more than selecting clips: an agent must preserve narrative intent across material preparation, timeline construction, post-production, and revision while leaving enough evidence to diagnose failures. We present \textbf{Crayotter}, an open-source multimodal multi-agent system for prompt-driven video editing. Crayotter organizes production into three phases: coverage-aware material preparation, artifact-based editing research, and tool-grounded timeline execution. Each phase externalizes inspectable artifacts, including coverage reports, multimodal analyses, editing blueprints, tool calls, and intermediate renders. These artifacts make an editing run traceable and allow failed segments to be diagnosed and selectively revised instead of requiring a full restart. We evaluate Crayotter on 23 editing themes against CapCut-Mate and CutClaw. Under human evaluation, Crayotter achieves an average score of 3.40/5, compared with 2.44 and 1.70 for the two baselines, with consistent gains in theme alignment, narrative coherence, and editing smoothness. We additionally describe a replayable trajectory schema and verifiable reward design that prepare these workflows for future policy optimization. Code, traces, and examples are publicly available at https://github.com/idwts/Crayotter.