Untrivial-ai/agent-orchestrator

Agent IDE that enables you to manage fleets of coding agents. It comes with an agentic orchestrator that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.

What it solves

Agent Orchestrator (AO) solves the problem of managing multiple coding agents working on a single project. While a single agent can handle a task, running several in parallel creates coordination challenges such as deciding work distribution, providing correct context, preventing branch collisions, and tracking progress through review and merge cycles.

How it works

AO is a local desktop workspace that acts as a supervisor for various coding agents. It uses a local daemon to monitor agent activity and source-control state.

  • Workers: These are isolated execution units. Each worker consists of one task, one coding agent, and its own isolated workspace (including a dedicated Git branch and worktree for Git-backed work).
  • The Orchestrator: A persistent planning agent that operates at a project-wide level. It handles high-level strategy, brainstorms approaches, and can break ambiguous goals into concrete tasks, spawning and delegating them to workers.
  • Kanban Board: A live operational view that derives the status of every worker (Working, Needs you, In review, Ready to merge) from session, pull request, and CI facts.

Who it’s for

Developers who use AI coding agents and want to move from single-task automation to a system of multiple agents working in parallel across a repository.

Highlights

  • Multi-Agent Coordination: Supports 26 different coding agents through a single supervised workflow.
  • Isolated Workspaces: Provides each worker with its own branch, worktree, and isolated browser profile to prevent state collisions.
  • Closed-Loop Feedback: Integrates CI and pull request reviews directly back to the agent that owns the work.
  • Native Interface Support: Allows users to interact with agents via structured Chat or the agent's own native terminal UI.

Related

  • Project
    777genius/agent-teams-ai

    A desktop orchestration layer for AI agent teams that allows agents from multiple providers to collaborate autonomously on coding and project tasks via a Kanban board.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a unified workspace for coordinating multiple AI coding agents, allowing them to share context and work within developer-controlled workflows.

  • Project
    solo-agent/solo

    A local-first workspace that coordinates multiple AI coding agents through shared channels, threaded task boards, and long-term memory.

  • Project
    agent-tower/core

    A command center for managing multiple AI agents, featuring a Kanban dashboard, automatic Git Worktree isolation for conflict-free coding, and multi-agent collaboration.

  • Project
    stablyai/orca

    An AI orchestrator that lets developers run multiple CLI-based coding agents in parallel isolated worktrees to compare results and accelerate development.