What problem does it solve?
Manually coordinating multiple parallel AI agent sessions across different development tools is time-consuming and error-prone when splitting complex tasks into independent workstreams.
Core Features & Use Cases
- Cross-harness orchestration: Manage parallel agent sessions across Claude Code, Codex, OpenCode, Cline, Gemini, and Qwen in a single tmux session.
- Pre-built workflow patterns: Ready-to-use templates for common use cases including research + implementation splits, multi-file feature development, test-fix loops, and parallel code review.
- Conflict-free collaboration: Git worktree integration guidance to avoid file conflicts between parallel agent workstreams.
- Use case example: Split a complex e-commerce checkout feature build into parallel tracks for payment processing, inventory management, and UI components, then merge all results into a single cohesive implementation.
Quick Start
Use the dmux-workflows skill to split your current checkout feature build into parallel agent tracks for payment processing, inventory management, and UI components, then merge all results once each track is complete.