Orchestrator.inc 开源 Agent 编排工作区：统筹 Claude Code、Codex 等 30+ 编程智能体，贯通从任务规划到 PR 合并全流程

面向 Agent 驱动开发的工作区

单个编程 Agent 可以搞定一项具体任务。但在整个项目中同时运行多个 Agent 则带来了截然不同的挑战：明确工作重心、清晰拆分任务、为每个 Agent 分配恰当的上下文、防止分支冲突，以及全程跟进每项变更直至审查与合并。

Orchestrator.inc 正是专为解决此类问题打造的本地桌面工作区。只需添加一个代码仓库，即可根据任务需求选用适合的编程 Agent、模型和交互界面创建 Worker 会话。对于基于 Git 的开发流程，Orchestrator.inc 会为该 Worker 分配独立的分支和工作树（worktree）。任务信息、对话历史、终端界面、变更文件、浏览器预览、Pull Request、CI 以及代码审查状态都会自始至终绑定在该会话中。

在桌面应用的底层，Orchestrator.inc 的本地守护进程（daemon）会实时监听 Agent 活动与版本控制状态。最终呈现的是整个项目的统一实时全景视图，而非一堆割裂的终端窗口、代码分支和浏览器标签页。

请下载适用于你所用平台的最新 Orchestrator.inc 桌面应用。Orchestrator.inc 会自动检查版本更新。

在 macOS 上，若应用无法打开并提示无法验证开发者，请右键点击应用并选择“打开”，然后再次点击“打开”。如果仍无法打开，请附带 Gatekeeper 诊断信息提交 Issue。具体需包含的诊断内容请参阅安装指南。

打开 Orchestrator.inc 并将其指向你希望管理的仓库。桌面应用会自动为你启动后台守护进程，无需通过 CLI 操作。有关 Agent CLI 配置与故障排除，请参阅安装指南。

Worker 执行专注的具体任务

Worker 是 Orchestrator.inc 的基础执行单元：对应一项任务、一个编程 Agent 以及一个独立隔离的工作区。当开发目标已经明确时，点击 New task 即可。描述预期产出、选择 Agent 和模型、附加相关文件，即可通过结构化 Chat 或其原生终端 UI 与 Agent 协同推进工作。

你可以随时打开任意 Worker 继续对话、接入其终端、检查文件变更、使用其独立的浏览器、审查其 Pull Request，或将 CI 和审查反馈重新传递给同一个 Agent。这让每个任务都具备清晰的独立性与可理解性，避免并行工作因上下文混杂在同一个共享环境中而失控。

Orchestrator 负责统揽项目的全局规划

项目编排器（Orchestrator）是 Orchestrator.inc 中的常驻规划与协调 Agent。它运作于单项任务之上，站在全局高度把控产品方向、技术策略、优先级排序以及全仓库的工作推进序列。

在正式编写代码前，你可以借助 Orchestrator 探索构想、头脑风暴产品与技术方案、推演权衡得失、识别高价值工作，并将模糊的目标转化为切实可行的计划。其项目级的对话流会持久保存目标、决策、约束条件及过往推演细节。它将这一规划历史与仓库上下文以及 Orchestrator.inc 的实时状态（包括活跃 Worker、任务归属、Pull Request、CI 及审查状态）紧密结合，确保规划既扎根于项目本身，又与当前正在进行的开发步调一致。

当方案具备可操作性后，Orchestrator 可以将其拆解为专注的子任务，生成或重定向 Worker，向各个 Worker 分发精准的上下文，跟踪其进度，并协调后续工作。Orchestrator 统管规划与分发委派；Worker 则负责具体实现、测试编写、代码提交及 Pull Request。

看板让整个系统清晰可视

无论是由你通过 New task 手动创建，还是由 Orchestrator 委派生成，所有 Worker 都会呈现在同一张实时看板上。Orchestrator.inc 会根据会话、Pull Request、CI 及审查数据动态确定每张卡片的位置，将看板转化为整个项目的运营级全景视图：

• Working（进行中）： 正在积极执行代码实现或等待下一条指令的 Worker
• Needs you（需要人工介入）： 被阻塞的会话、缺少输入、CI 失败、收到变更请求或连接信号丢失
• In review（审查中）： 处于开启或草稿状态、正在等待检查或审查的 Pull Request
• Ready to merge（准备合并）： 已获批准或满足合并条件的工作，已合并的会话在归档前仍会保持可见

每张卡片都将任务、Agent、分支、活动、Pull Request 和当前状态聚合在一起。点击卡片即可查看对话历史或终端、变更文件、PR 摘要、审查意见以及实时预览。看板清晰展示了哪些工作正在推进、哪些环节受阻，以及你的精力投入在何处能带来最大的价值回报。

从构想到合并的单一工作流

1. 从适宜的层级起步。 直接将明确的任务指派给 Worker，或者与项目 Orchestrator 共同构思更宏观的目标，由其细化成实施计划。
2. 委派专注的工作。 自行启动 Worker，或让 Orchestrator 在配置好上下文与归属权后自动创建它们。
3. 在隔离环境中构建。 每个基于 Git 的 Worker 都会获得独立的分支和工作树（worktree）；独立 Agent 则获得 Orchestrator.inc 管理的免分支目录，无需绑定项目或仓库。
4. 实时监管运行状态。 Orchestrator.inc 跟踪 Agent 活动、Pull Request、CI、审查反馈以及合并冲突，并将这些事实实时同步到看板上。
5. 闭环反馈回路。 直接检查任一 Worker，与 Orchestrator 共同做出项目级决策，并将可操作的失败信息或审查评论反哺给负责该工作的对应 Agent。

Orchestrator.inc 能够与你现有的编程 Agent 及版本控制工作流无缝融合。Agent 保留了各自的原生优势；Orchestrator.inc 则提供项目上下文、隔离执行环境、多方协作机制与全局运维视图，使它们能够作为一套完整的系统协同运转。

Pull Request 与 Agent 审查

CI、可合并性、审查者状态以及交互式 Agent 审查与 Worker 并列展示，随后可将提出的变更请求返回给同一负责人。

Agent 可控的浏览器

在 Worker 交互界面旁实时预览并检查其本地应用。临时浏览器配置文件（profiles）按 Worker 实现隔离；指定名称的配置文件则可在不同会话间故意复用已保存的 Cookie 与本地存储。 |

原生交互界面，统一监管

使用结构化 Chat 或 Agent 的原生终端 UI，同时 Orchestrator.inc 会将任务上下文、工作区状态和反馈集中在一处统一管理。 |

统一监管工作流中的编程 Agent 测试运行装置（Harness）。 Worker、Chat 和 Reviewer 的支持情况有所不同；最新支持矩阵请参阅下方链接的能力目录。

Claude Code	Codex	Cursor
opencode	Aider	GitHub Copilot
Grok	Kimi	Pi
Amp	Auggie	Droid
Crush	Cline	Goose
Qwen	Continue	Devin
Kiro	Kilo Code	Vibe
Muse	Agy	Autohand
Kimchi	Prime Agent	OMP
fx	Unreal Agent	MiMo Code
Gemini CLI	DeepSeek	OpenCode 2
Codewhale	Command Code	OpenHands

浏览 Agent 配置指南 →

根据当前场景选择最适合的交互方式：结构化 Chat 或 Agent 的原生终端 UI。

提交 Bug 报告

A workspace for agent-driven development

One coding agent can handle a task. Running several across a project creates a different job: deciding what matters, splitting work cleanly, giving each agent the right context, preventing branch collisions, and following every change through review and merge.

Orchestrator.inc is a local desktop workspace built for that job. Add a repository and create a worker session with the coding agent, model, and interface that fit the task. For Git-backed work, Orchestrator.inc gives the worker its own branch and worktree. The task, conversation, terminal, changed files, browser preview, pull request, CI, and review state stay attached to that session from start to finish.

Behind the desktop app, Orchestrator.inc's local daemon watches agent activity and source-control state. The result is a shared, live view of the project instead of a collection of disconnected terminals, branches, and browser tabs.

Download the latest Orchestrator.inc desktop app for your platform. Orchestrator.inc checks for updates automatically.

On macOS, if the app will not open and says the developer cannot be verified, right-click it and choose Open , then Open again. If that still does not open it, please open an issue with Gatekeeper diagnostics. See the installation guide for what to include.

Open Orchestrator.inc and point it at the repository you want Orchestrator.inc to manage. The desktop app runs the daemon for you, so no CLI is required. See the installation guide for agent CLI setup and troubleshooting.

Workers execute focused tasks

A worker is Orchestrator.inc's unit of execution: one task, one coding agent, and one isolated workspace. Use New task when the work is already clear. Describe the outcome, choose an agent and model, attach relevant files, and work with the agent in structured Chat or its native terminal UI.

Open a worker at any time to continue the conversation, attach to its terminal, inspect its changes, use its isolated browser, review its pull request, or send CI and review feedback back to the same agent. This makes each task independently understandable and keeps parallel work from collapsing into one shared context.

The orchestrator plans across the project

The project orchestrator is Orchestrator.inc's persistent planning and coordination agent. It works at the level above individual tasks: the product direction, technical strategy, priorities, and sequence of work across the repository.

Use the orchestrator to explore an idea before implementation, brainstorm product and technical approaches, reason through tradeoffs, identify high-impact work, and turn an ambiguous outcome into a concrete plan. Its project-scoped conversation preserves goals, decisions, constraints, and earlier reasoning. It combines that planning history with repository context and live Orchestrator.inc state, including active workers, ownership, pull requests, CI, and reviews. This keeps planning grounded in both the project and the work already underway.

When a plan becomes actionable, the orchestrator can break it into focused tasks, spawn or redirect workers, pass each worker the relevant context, follow their progress, and coordinate follow-up work. The orchestrator owns planning and delegation; workers own implementation, tests, commits, and pull requests.

The Kanban keeps the system legible

Every worker appears on the same live board, whether you started it from New task or the orchestrator delegated it. Orchestrator.inc derives each card's position from session, pull request, CI, and review facts, turning the Kanban into an operational view of the project:

• Working: workers that are actively implementing or ready for another instruction
• Needs you: blocked sessions, missing input, failed CI, requested changes, or lost signals
• In review: open and draft pull requests waiting on checks or review
• Ready to merge: approved or mergeable work, with merged sessions kept visible until they are archived

Each card keeps the task, agent, branch, activity, pull request, and status together. Open it to inspect the conversation or terminal, changed files, PR summary, reviews, and preview. The board shows what is moving, what is blocked, and where your attention will have the most impact.

One workflow, from idea to merge

1. Start at the right level. Give a clear task directly to a worker, or develop a larger outcome with the project orchestrator and let it shape the plan.
2. Delegate focused work. Start workers yourself or have the orchestrator create them with the context and ownership they need.
3. Build in isolation. Every Git-backed worker gets its own branch and worktree; standalone agents get Orchestrator.inc-managed branchless directories without requiring a project or repository.
4. Supervise live state. Orchestrator.inc follows agent activity, pull requests, CI, review feedback, and merge conflicts, then reflects those facts on the Kanban.
5. Close the feedback loop. Inspect any worker directly, make project-level decisions with the orchestrator, and return actionable failures or review comments to the agent that owns the work.

Orchestrator.inc works with the coding agents and source-control workflow you already use. Agents keep their native strengths; Orchestrator.inc supplies the project context, isolated execution, coordination, and operational view that make them work as a system.

Pull requests and agent reviews

Keep CI, mergeability, reviewer state, and interactive agent reviews beside the worker, then return requested changes to the same owner.

Agent-controllable browser

Preview and inspect a worker's local app beside its interface. Temporary browser profiles are isolated per worker; named profiles deliberately reuse saved cookies and storage across sessions. |

Native interfaces, one supervisor

Use structured Chat or the agent's native terminal UI while Orchestrator.inc keeps task context, workspace state, and feedback in one place. |

Coding agent harnesses in one supervised workflow. Worker, Chat, and reviewer support differ; see the capability catalog linked below for the current matrix.

Claude Code	Codex	Cursor
opencode	Aider	GitHub Copilot
Grok	Kimi	Pi
Amp	Auggie	Droid
Crush	Cline	Goose
Qwen	Continue	Devin
Kiro	Kilo Code	Vibe
Muse	Agy	Autohand
Kimchi	Prime Agent	OMP
fx	Unreal Agent	MiMo Code
Gemini CLI	DeepSeek	OpenCode 2
Codewhale	Command Code	OpenHands

Browse agent setup guides →

Use the interface that fits the moment: structured Chat or the agent's native terminal UI.

Open a bug report from your own GitHub account. A few sentences in your own words about what you did and what went wrong are enough. Add what you expected, reproduction steps, your Orchestrator.inc version and OS, or a screenshot if you have them; these are helpful, not prerequisites.

A local coding agent can help you clarify the report and gather evidence using the bug-triage skill. Keep the issue body focused on your observations, with agent-collected logs, database excerpts, and investigation notes in separate attachments. Review any draft before submitting it under your own account. Please don't ask a bot to file issues on your behalf; reporter attribution matters.

For help describing a problem, join the bug-triaging channel on Discord. See contribution guidance for more detail.

Contributions are welcome across code, docs, triage, examples, and tests.

git clone https://github.com/OrchestratorInc/agent-orchestrator.git
cd agent-orchestrator

Start with the development guide for prerequisites, local setup, and test commands. Read CONTRIBUTING.md before opening a pull request, and use GitHub Issues for bugs and feature requests.

Document	Start here when you need
Product documentation	Installation, agent setup, and day-to-day product usage.
docs/documentation-map.md	Which docs are human-facing, which are machine-readable contracts, and which wins on drift.
docs/architecture.md	Backend mental model, lifecycle, persistence, CDC, status derivation, and daemon boundaries.
docs/backend-code-structure.md	Package ownership and where each backend concern belongs.
docs/cli/README.md	CLI behavior and daemon route mapping.
docs/development.md	Prerequisites, build steps, running tests, and troubleshooting for local development.
docs/STATUS.md	What currently ships on main and what remains in flight.

Community

Join Discord for help and contributor discussion, follow @useOrchestrator for updates, or start a conversation in GitHub Issues.

Product telemetry is designed to exclude your code, prompts, agent conversations, and credentials.
Orchestrator.inc collects limited usage and reliability telemetry to improve the product. Learn what we collect and how to turn off desktop telemetry.

Orchestrator.inc is available under the Apache License 2.0.