Online discussion among civilian is important and essential for next-generation democracy. Crowd-scale online discussion platforms are receiving great attention as potential nextgeneration methods for smart democratic citizen platforms. Such platforms require support functions that can efficiently achieve a consensus, reasonably integrate ideas, and discourage flaming. In this work, we propose D-agree platform in which an automated facilitation agent helps to manage crowd-scale online discussions. An automated facilitator agent extracts the discussion structure from the texts posted in discussions by people. In this paper, we present our current implementation of D-agree, a crowd-scale discussion support system based on an automated facilitation agent, which extracts discussion structures from text discussions, analyzes them, and posts facilitation messages. We conducted a large-scale social experiment with Nagoya City s local government. The results present that our automated facilitation agents succeeded to gather more opinions from people. Furthermore, we present hyperdemocracy, a vision for the next generation democratic platform.