OpenScreen 2 launches here tomorrow. It plans zooms from your clicks, and an AI agent can cut the recording over MCP, but every demo still has a part people fix by hand.
What is it for you? I'll use the answers to decide what the agent handles next.
Record your screen and the demo looks great on the first take: zooms planned from your clicks, smooth cursor, 3D camera moves, cursor themes, backgrounds and webcam layouts. Then let your AI agent do the edit over MCP, or cut the video yourself by deleting words in the transcript. Windows, macOS and Linux. Free, MIT, no account, no watermark.
