Chorus Agent工作流
Chorus Agent工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.2 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
Chorus Agent工作流 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.2 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
Chorus Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
📖 中文文档
Chorus Agent工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：npm 全局安装 npm install -g chorus # 方式二：npx 直接运行（无需安装） npx chorus --help # 方式三：项目依赖安装 npm install chorus # 方式四：从源码运行 git clone https://github.com/Chorus-AIDLC/Chorus cd Chorus npm install npm start
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
chorus --help
# 基本用法
chorus [options] <input>
# Node.js 代码中使用
const chorus = require('chorus');
const result = await chorus.run(options);
console.log(result);
# chorus 配置说明 # 查看配置选项 chorus --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export CHORUS_CONFIG="/path/to/config.yml"
简介
<p align="center"> <img src="docs/images/chorus-slug.png" alt="Chorus" width="240" /> </p>
<p align="center"><strong>The Agent Harness for AI-Human Collaboration</strong></p>
<p align="center"> <a href="https://discord.gg/SwcCMaMmR"> <img src="https://img.shields.io/badge/Discord-Join%20us-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"> </a> <a href="https://github.com/Chorus-AIDLC/Chorus/actions/workflows/test.yml"> <img src="https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/ChenNima/f245ebf1cf02d5f6e3df389f836a072a/raw/coverage-badge.json" alt="Coverage"> </a> </p>
<p align="center"><a href="README.zh.md">中文</a></p>
Chorus is an agent harness — the infrastructure that wraps around LLM agents to manage session lifecycle, task state, sub-agent orchestration, observability, and failure recovery. It lets multiple AI Agents (with fine-grained, configurable permissions) and humans collaborate through the full workflow from requirements to delivery.
Inspired by the AI-DLC (AI-Driven Development Lifecycle) methodology. Core philosophy: Reversed Conversation — AI proposes, humans verify.
---
What's New
v0.12.0 — Addressable daemon instances: one chorus daemon can serve multiple working directories (--cwd), and each (agent, host, cwd) becomes an individually visible, individually targetable instance across presence, @-mention, and assignment. Pin an instance once on an idea and its proposals, tasks, and wakes inherit it; pinned wakes are delivered to exactly that instance instead of broadcast. Comment @-mentions render as live online-status badges, and comments switch to cursor-based infinite scroll.
v0.11.0 — The Chorus Daemon: chorus daemon turns your machine into a resident agent runtime that wakes a local Claude Code on each dispatch. An Agent Connections surface gives live observability and control — streaming transcripts, instruction injection, and interrupt / resume — and a "Verify Elaborate" button wakes the assigned agent to write the proposal.
v0.10.0 — Single-parent idea lineage: an idea may derive a child or be attached under another, forming a forest. The relation is intentionally weak — a parent surfaces a read-only "+N derived" rollup and does not constrain any child's elaboration, proposal, or task flow. Idea browsing consolidates onto the Dashboard (a three-way Ideas / Lineage / Stats view switch with an adaptive default); the standalone Idea List page is retired and its URLs 308-redirect to the Dashboard.
v0.9.4 — OpenClaw plugin rewritten on the OpenClaw 2026.4.27 Plugin SDK (native MCP registration, runEmbeddedAgent for SSE wake, reviewers as native skills); Codex plugin hooks now ship inside the package, with an installer that cleans up legacy hook copies in the user directory.
v0.9.0 — Brainstorm skill for fuzzy ideas (open-ended chat before structured Q&A) and idea-completion reports (every shipped idea gets a Summary / Decisions / Follow-ups writeup, surfaced on the idea overview).
v0.8.0 — OpenSpec-aware mode (Claude Code): auto-activates when an openspec/ directory and the openspec CLI are both present, adds /opsx/{explore,propose,apply,archive} and a post-verify archive-trigger hook.
Full changelog: CHANGELOG.md
---
Features
- Session Lifecycle — Persistent sessions with heartbeats, auto-expiry, and failure recovery - Task DAG — Dependency modeling, cycle detection, and interactive visualization - Kanban — Real-time task flow with Worker badges and agent presence - Multi-Agent Collaboration — Claude Code Agent Teams (Swarm Mode) for parallel execution - Fine-Grained Agent Permissions — 5 resources × 3 actions grid with preset + custom combinations (details) - Chorus Plugin — Lifecycle hooks automate session create/close, heartbeats, and context injection - Requirements Elaboration — Structured Q&A rounds before proposal creation - Proposal Approval Flow — PM drafts, Admin approves, drafts materialize into real entities - Notifications — In-app + SSE push + Redis Pub/Sub with per-user preferences (design doc) - @Mention — Tiptap autocomplete, permission-scoped search, mention notifications (design doc) - Activity Stream — Full audit trail with session attribution - Universal Search — Cmd+K across 6 entity types, 3 scope levels, snippet generation (design doc) ---
Idea & Requirements Elaboration
PM Agents clarify requirements through structured Q&A rounds before creating Proposals. The panel shows idea details alongside completed elaboration rounds with answers and category tags.
Other deployment options
| Method | Command |
|---|---|
| **npm** (simplest) | npm i -g @chorus-aidlc/chorus && chorus |
| **Docker (standalone)** | [docker compose -f docker-compose.local.yml up](#quick-start-with-docker-recommended) |
| **Docker (full stack)** | [docker compose up](#quick-start-with-docker-recommended) (PostgreSQL + Redis + Chorus) |
| **AWS CDK** | [Deploy to AWS](#deploy-to-aws) |
Getting Started
Quick Start with Docker (Recommended)
No build tools or external databases required. The image bundles PGlite (embedded PostgreSQL):
git clone https://github.com/Chorus-AIDLC/chorus.git
cd chorus
DEFAULT_USER=admin@example.com DEFAULT_PASSWORD=changeme \
docker compose -f docker-compose.local.yml up -dOpen http://localhost:8637 and log in with the credentials above.
Data is persisted in a Docker volume. The embedded mode is single-instance only (no Redis).
Production Deployment (PostgreSQL + Redis)
For production with multiple replicas:
DEFAULT_USER=admin@example.com DEFAULT_PASSWORD=changeme \
docker compose up -dSee Docker Documentation for all environment variables and configuration options.
---
Local Development (no Docker)
Prerequisites: Node.js 22+, pnpm 9+
cp .env.example .env
pnpm install
pnpm dev:local # Dev server on http://localhost:8637PGlite runs embedded PostgreSQL on port 5433. Data stored in .pglite/ — delete to reset.
Deploy to AWS
./install.shThe interactive installer provisions VPC, Aurora Serverless v2, ElastiCache Serverless, ECS Fargate, and ALB with HTTPS. Configuration saved to default_deploy.sh for re-deploys.
Quick Start
Run Chorus locally with two commands — no database, no Docker, no config files needed.
npm install -g @chorus-aidlc/chorus
chorusThat's it. Chorus starts with an embedded PostgreSQL (PGlite), runs migrations automatically, and opens at http://localhost:8637.
Note: PGlite is an embedded, single-process PostgreSQL — great for local single-user usage, but its connection handling has limits under concurrent load. If you plan to run multiple agents or users simultaneously, use an external PostgreSQL via DATABASE_URL=postgresql://... or the full Docker Compose stack.
Default login: admin@chorus.local / chorus
Screenshots
Options
```bash
AI-DLC Workflow
Idea ──> Proposal ──> [Document + Task DAG] ──> Execute ──> Verify ──> Done
^ ^ ^ ^ ^ ^
Human idea:write proposal:write task:write *:admin *:admin
creates + elaborate + drafts + reports + verifies + closesThe labels under each stage are the permissions an actor needs at that stage — granted to a human, an Agent (preset or Custom), or both. There are no fixed roles; any combination of the 5 × 3 permission matrix is possible. See docs/PERMISSIONS.md.
---
Packages
| Package | Description |
|---|---|
[packages/openclaw-plugin](packages/openclaw-plugin) | **OpenClaw Plugin** — Connects [OpenClaw](https://openclaw.ai) to Chorus via persistent SSE + MCP bridge. |
[packages/chorus-cdk](packages/chorus-cdk) | **AWS CDK** — Infrastructure-as-code for deploying Chorus to AWS. |
OpenSpec mode (opt-in, plugin 0.8.1+)
PM agents that have the OpenSpec CLI installed can author proposals in a structured proposal.md + design.md + specs/<capability>/spec.md layout. Local files are the working copy and Chorus documentDrafts are the mirror; reviewers see a predictable shape (## ADDED Requirements, ### Requirement:, #### Scenario:) instead of free-form Markdown. A PostToolUse hook on chorus_admin_verify_task injects an openspec archive <slug> reminder when the last task of an OpenSpec idea is verified, so finalized specs are merged into the long-term spec set right after sign-off. The mode is strictly opt-in: when openspec is not installed, behavior is unchanged. Master switch on Claude Code is enableOpenSpec (plugin userConfig, default true); both clients also honor CHORUS_OPENSPEC_MODE=off. No new MCP tools or schema changes ship in this mode; the canonical skill reuses the existing chorus_pm_* draft and document tools, with mirror calls routed through the chorus-api.sh wrapper to keep multi-thousand- line markdown out of LLM context. See OPENSPEC_MODE.md for the full guide.
---
Chorus 是一个 AI 人机协作的代理工具，旨在促进人机之间的高效协作。
Chorus 的功能包括会话生命周期管理、任务依赖关系图、Kanban 流程管理、多代理协作、细粒度代理权限管理等。
Chorus 需要一个稳定的网络环境，支持多种数据库和消息队列系统，包括 PostgreSQL、Redis 等。
Chorus 支持多种部署方式，包括 npm、Docker、AWS CDK 等，用户可以根据自己的需求选择合适的部署方式。
Chorus 的使用教程包括快速启动、配置管理、任务管理等方面，用户可以通过这些教程快速上手 Chorus。
Chorus 的配置管理包括 MCP、环境变量、关键参数等方面，用户可以通过这些配置项来定制 Chorus 的行为。
Chorus 的工作流包括idea、proposal、document、task、execute、verify、done等阶段，用户可以通过这些阶段来管理项目的整个生命周期。
Chorus是AI工作流领域的优秀开源项目，融合Agent框架和人机协作理念，841星的热度反映社区认可度。TypeScript实现便于集成，适合现代AI应用开发。
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
- Docker：Chorus 提供官方镜像，docker compose up 一键启动
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 跨境业务、多语言内容运营团队
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- 容器内无法访问宿主机 localhost — 使用 host.docker.internal
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
该工具使用 AGPL-3.0 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft，网络服务端使用也需开源，SaaS 使用受限。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，Chorus Agent工作流 在Agent工作流赛道中表现稳健，质量优秀。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | Chorus |
| 原始描述 | 开源AI工作流：The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven 。⭐841 · TypeScript |
| Topics | AI工作流Agent框架人机协作AI代理TypeScript |
| GitHub | https://github.com/Chorus-AIDLC/Chorus |
| License | AGPL-3.0 |
| 语言 | TypeScript |
收录时间：2026-05-17 · 更新时间：2026-05-19 · License：AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。