a

agent-orchestrator

An IDE for managing parallel coding agents, automatically handling CI fixes, merge conflicts, and code reviews.

🌍 OverseasFreeOpen sourceDev开源桌面操作
Platforms: DesktopCLI
Region
Overseas
Pricing
Free
Open source
Yes
GitHub Stars
★ 8.6k
Source
GitHub
Added
2026-07-29
Last verified
2026-07-29
agent-orchestrator

Overview

Agent Orchestrator is a meta-level agent IDE designed to run parallel AI coding agents. It provides a shared workspace for terminal agents such as Claude Code and Codex, enabling centralized supervision of their sessions, terminals, branches, pull requests, and feedback loops. The agents still handle the actual coding, while AO offers the framework around them: isolated workspaces, real-time terminal access, session state tracking, PR awareness, and automated cycles that feed CI failures, review comments, and merge conflicts back to the correct agents. This turns parallel agent workflows into a manageable process.

Key features

  • Manage parallel coding agents
  • Isolated workspaces
  • Real-time terminal control
  • Automated CI fix handling
  • Merge conflict and code review resolution

Use cases

Parallel coding with multiple agentsAutomated CI/CD pipelinesCode review and merge conflict resolutionProject management and collaboration

Pros

  • Increases coding efficiency
  • Simplifies management of parallel workflows
  • Supports multiple coding agents
  • Real-time monitoring and feedback

Limitations / notes

  • Requires some learning curve
  • Dependent on network connectivity

Who it's for

DevelopersTeam managersProject managers

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

Is it free?

Yes, the project is open source and available for free use.

Does it support Chinese?

Documentation and interface are primarily in English, but you can add Chinese support yourself.

Can it be used commercially?

Yes, it is licensed under Apache-2.0, allowing commercial use.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.