Dynamo: Give Your Coding Agents Eyes and Your PR Reviewers Proof

说明与用途

Dynamo 为自主代理和浏览器自动化提供可视化监控，消除损坏的视频和过度的令牌使用。

问题

When an AI coding agent or browser-use sandbox fails in CI, the agent runs headless without visual feedback, producing large stack traces and a single static PNG that does not show which action triggered the regression.

结果

Dynamo eliminates silent failures, corrupt recordings, and token waste, enabling reliable visual debugging for autonomous agents and browser automation.

工作流

• Enter VisualHarness context to start Xvfb and ffmpeg
• Run agent or browser inside the context
• Log actions with timestamps
• Take mid-run screenshots if needed
• Export artifacts (video, GIF, VLM keyframes) on exit, even if exception occurs

证据

When an AI coding agent or browser-use sandbox fails in CI at 2:00 AM, everyone flies blind.

来源

Standard ffmpeg holds the MP4 container index in memory until a clean shutdown. When an unhandled exception or CI job timeout triggers SIGKILL, the header is never written: DIY script, agent killed mid-run : moov atom not found (0 bytes, 0 frames — unrecoverable)

来源

Naive time-based sampling captures 1 frame per wall-clock second regardless of screen activity. In our benchmark, 19 of 50 consecutive frames were pixel-identical, burning 56,100 tokens on static screens while waiting on network I/O.

来源

Dynamo is a headless, zero-dependency Python visual and video harness for coding agents, Playwright browser automation, and computer-use sandboxes.

来源