revmux
Supervised multi-agent code review orchestrated by AI coding agents
Visit revmux.com ↗What is revmux?
revmux runs structured reviews by spawning and supervising multiple AI models (Claude and Codex) as subprocesses, then returning verified findings as JSON or markdown. It's launched by coding agents rather than manually, treating branches, pull requests, design documents, and issues uniformly through a stable contract. Built with Claude, revmux provides visibility into each agent's work, automatic stall detection with retry logic, and a complete run archive on disk. The review standard is defined by configuration files (roster, lenses, severity thresholds, stages) rather than ad hoc prompts, ensuring consistency across contributors and maintainers.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered revmux automatically. Evidence: Rising on GitHub: agent files (claude-code) in umputun/revmux. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces

Manage teams of AI agents to run your business from one dashboard

Persistent memory for AI agents across Claude Code, Cursor, and MCP clients