Agenthub

Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub:init, /hub:spawn, /hub:status, /hub:eval, /hub:merge, /hub:board, /hub:run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.

by @alirezarezvani 10 skills

Skills in this plugin

10
  1. ▌
    Run · alirezarezvani
    Execute the full AgentHub competition lifecycle in a single command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.
    29.8k repo stars
  2. ▌
    Eval · alirezarezvani
    Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
    29.8k repo stars
  3. ▌
    Init · alirezarezvani
    Create a new AgentHub collaboration session with task, agent count, and evaluation criteria for multi-agent competitions.
    29.8k repo stars
  4. ▌
    Board · alirezarezvani
    Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.
    29.8k repo stars
  5. ▌
    Hub Init · alirezarezvani
    Use for /hub-init, or to start an AgentHub competition: task, agent count and evaluation criteria.
    29.8k repo stars
  6. ▌
    Merge · alirezarezvani
    Merge the winning agent's branch into the base branch, archive losing branches via git tags, and clean up worktrees after an AgentHub competition session.
    29.8k repo stars
  7. ▌
    Hub Status · alirezarezvani
    Use for /hub-status, or to check AgentHub agent progress, branches and DAG state.
    29.8k repo stars
  8. ▌
    Spawn · alirezarezvani
    Launch N parallel subagents in isolated git worktrees to compete on a session task.
    29.8k repo stars
  9. ▌
    Status · alirezarezvani
    Display DAG state, agent progress, and branch status for an AgentHub session.
    29.8k repo stars
  10. ▌
    Agenthub · alirezarezvani bundle
    Spawns multiple parallel AI agents that compete on the same task using isolated git worktrees, evaluates results, and merges the best solution.
    29.8k repo stars