Codex Orchestration 是一个 Codex 插件,通过引入 Planner(规划器)、Advisor(顾问)和 Executor(执行器)角色,在 Codex 的控制下协调多个模型(如 Claude Fable 5)进行规划、审查和实现任务。

Stars

551

7 天增长

暂无数据

Fork 数

55

开放 Issue

0

开源协议

MIT

最近更新

2026-07-26

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

它允许在 Codex 内实现多模型编排,用户可以将外部模型(如 Claude Fable 5)用于专门的规划和审查角色,并具有自动化的工作流门控和潜在的并行执行能力,从而提升效率。

适合谁使用

  • 使用 Codex 并希望在代码生成前进行更强规划的开发者
  • 希望为不同角色使用不同 AI 模型来协同工作的团队
  • 希望通过将任务分配给低成本执行器来减少高级模型 API 限制的用户

典型使用场景

  • 使用 Claude Fable 5 制定计划,GPT-5.6 Sol 审查,然后由 Luna 执行
  • 并行运行多个执行器以加速独立子任务的实现
  • 设置一个可重复的工作流,自动将模型角色应用到新的 Codex 任务中

项目优势

  • 模块化的角色分离(规划器、顾问、执行器),具有清晰的安全门控和最多 5 次审查限制
  • 能够将外部模型如 Claude Fable 5 引入 Codex,无需额外 API 密钥
  • 通过并行执行器可能实现高达 2 倍加速,并减少约 40% 的高级模型使用限制

使用前须知

  • Codex 仍然是根协调者,插件无法覆盖 Codex 的权限或委托决策
  • 需要兼容的模型和提供商;Fable 5 是唯一捆绑的跨提供商模型
  • 性能和速度提升取决于任务、模型、上下文和重试次数,不作保证

README 快速开始

Codex Orchestration

Bring models like Claude Fable 5 and Claude Opus 5 into Codex, give each model a role, and let Codex coordinate the work.

What is it?

Codex Orchestration adds four simple roles to a Codex task:

  • Planner creates the plan and improves it after feedback. It is optional; when omitted, your current Codex model plans.
  • Advisor reviews the plan, finds important gaps, and approves it when it is ready. It is optional.
  • Designer turns approved requirements into a bounded visual, UX, interaction, information-architecture, or design-system handoff. It is optional.
  • Executor implements the approved plan. It is required for setup.

The model selected for the Codex task remains in charge. It passes work between the roles, checks every result, and gives you the final answer.

How it works

                         YOUR TASK
                             |
                             v
                  CODEX COORDINATES THE WORK
                             |
                             v
               PLANNER CREATES THE FIRST PLAN
              Fable 5, another model, or Codex
                             |
                             v
                    ADVISOR REVIEWS IT
                       finds real gaps
                             |
                   needs work? -- yes --+
                             |            |
                            no            v
                             |      PLANNER IMPROVES IT
                             |            |
                             +, advisor: , designer: , executor: 
  • Omit planner to use the current Codex model as Planner.
  • Omit advisor when you do not want plan review.
  • Omit designer when you do not need a separate design handoff.
  • executor is required.
  • Planner and Advisor must use different configured model routes so the review is independent.

Role labels are literal. A model after planner: plans; a model after advisor: reviews; a model after designer: designs; a model after executor: implements. Codex must never move a model to a different role because that model was used differently in an older plugin version. If you omit Designer, the workflow has no Designer. If you specify Planner and Executor but omit Advisor, the workflow has no Advisor.

When every requested route is ready in the current task, the plugin c

项目描述

Bring any model to Codex, assign them any role, use them in /goal or any workflow.

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

lopopolo
精选
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI 与机器学习AI 智能体
2,390
slvDev
精选
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI 与机器学习大语言模型
1,960
littledivy
精选
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI 与机器学习
1,482