agent-swarm Agent工作流
经 AI Skill Hub 精选评估，agent-swarm Agent工作流 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.2 分，适合有一定技术背景的用户使用。
📚 深度解析
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
agent-swarm Agent工作流 依赖 TypeScript 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 TypeScript 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 agent-swarm Agent工作流 的版本更新，及时通知重要功能变化。
📋 工具概览
基于Claude的开源多代理AI编码框架，支持Agent协作与工作流编排。提供swarm模式分布式处理能力，适合需要复杂AI编码任务自动化、多智能体协作的开发者和企业。
agent-swarm Agent工作流 是一款基于 TypeScript 开发的开源工具，专注于 多代理系统、Claude集成、AI编码 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
📖 中文文档
基于Claude的开源多代理AI编码框架，支持Agent协作与工作流编排。提供swarm模式分布式处理能力，适合需要复杂AI编码任务自动化、多智能体协作的开发者和企业。
agent-swarm Agent工作流 是一款基于 TypeScript 开发的开源工具，专注于 多代理系统、Claude集成、AI编码 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：npm 全局安装 npm install -g agent-swarm # 方式二：npx 直接运行（无需安装） npx agent-swarm --help # 方式三：项目依赖安装 npm install agent-swarm # 方式四：从源码运行 git clone https://github.com/desplega-ai/agent-swarm cd agent-swarm npm install npm start
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
agent-swarm --help
# 基本用法
agent-swarm [options] <input>
# Node.js 代码中使用
const agent_swarm = require('agent-swarm');
const result = await agent_swarm.run(options);
console.log(result);
# agent-swarm 配置说明 # 查看配置选项 agent-swarm --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 AGENT_SWARM_CONFIG="/path/to/config.yml"
简介
<p align="center"> <a href="https://github.com/desplega-ai/agent-swarm/stargazers"><img src="https://img.shields.io/github/stars/desplega-ai/agent-swarm?style=flat-square&color=yellow" alt="GitHub Stars"></a> <a href="https://github.com/desplega-ai/agent-swarm/blob/main/LICENSE"><img src="https://img.shields.io/github/license/desplega-ai/agent-swarm?style=flat-square" alt="MIT License"></a> <a href="https://github.com/desplega-ai/agent-swarm/pulls"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen?style=flat-square" alt="PRs Welcome"></a> </p>
<p align="center"> <b>An engine to make your company AI Native</b><br/> <sub>Built by <a href="https://desplega.sh">desplega.sh</a> — by builders, for builders.</sub> </p>
[!TIP] This repo evolves every single day. Watch now →
<p align="center"> <video src="https://github.com/user-attachments/assets/e220712e-c54d-4f46-b059-bac04639d229" controls muted playsinline width="720"></video> </p> <p align="center"> <sub>▸ <a href="./assets/agent-swarm.mp4">daily evolution</a> · <a href="./assets/agent-swarm-slack-to-pr.mp4">slack → pr</a> · <a href="./assets/video-source">Making of</a></sub> </p>
<p align="center"> <a href="https://agent-swarm.dev"> <img src="https://img.shields.io/badge/Website-agent--swarm.dev-000?style=for-the-badge" alt="Website"> </a> <a href="https://docs.agent-swarm.dev"> <img src="https://img.shields.io/badge/Docs-docs.agent--swarm.dev-amber?style=for-the-badge" alt="Docs"> </a> <a href="https://app.agent-swarm.dev"> <img src="https://img.shields.io/badge/Dashboard-app.agent--swarm.dev-blue?style=for-the-badge" alt="Dashboard"> </a> <a href="https://discord.gg/KZgfyyDVZa"> <img src="https://img.shields.io/badge/Discord-Join%20Community-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Join Discord"> </a> <a href="https://x.com/desplegalabs"> <img src="https://img.shields.io/badge/𝕏-@desplegalabs-000?style=for-the-badge&logo=x&logoColor=white" alt="Follow on X"> </a> <a href="https://www.linkedin.com/company/desplega-labs/"> <img src="https://img.shields.io/badge/LinkedIn-Desplega%20Labs-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white" alt="Desplega Labs on LinkedIn"> </a> </p>
Agent Swarm is your Company's Compounding Intelligence Layer. A system of AI agents that remember, reason, act and get better with every task.
AI-Native · Compounds · Presence · Harness & LLM-Agnostic · Your Infra · Your Memory ·
Highlights
- Lead/worker orchestration in Docker — isolated dev environments, priority queues, pause/resume across deploys. Architecture →
- Compounding memory & persistent identity — agents remember past sessions and evolve their own persona, expertise, and notes. Memory → · Agents →
- Hybrid memory recall + in-place edits — memory retrieval can blend vector and full-text ranking, and agents can correct an existing memory without losing its ID or history. Memory → · MCP tools →
- Multi-channel inputs — Slack, GitHub, GitLab, email, WhatsApp, Linear, Jira, and the HTTP API all create tasks. Integrations
- Workflow engine with Human-in-the-Loop — DAG-based automation with approval gates, retries, and structured I/O. Workflows →
- Scheduled & recurring tasks — cron-based automation for standing work, with schedules that can target agent tasks, workflows, or catalog scripts. Scheduling →
- Durable script workflows — launch background script runs, inspect their journals, and track them from the dashboard when a one-shot
script-runis too small. Guide → - Scripts as external APIs — expose a saved script as a public
POST /api/x/script/<id>endpoint with optional bearer auth, typed input validation, and per-endpoint usage tracking. Guide → - Typed script API connections — lead-managed OpenAPI connections let scripts call approved external APIs through generated
ctx.api.*clients while credential bindings keep raw secrets out of source and args. Guide → - E2B-backed eval harness — run a scenario × harness-config matrix against real swarm stacks, capture transcripts/artifacts, and grade outcomes with deterministic checks plus LLM or agentic judges. Guide →
- Harness & LLM agnostic — run with Claude Code, Claude Bridge, OpenAI Codex, pi-mono (Anthropic, OpenRouter, or Amazon Bedrock), Devin, Claude Managed Agents, raw LLMs, or opencode. Tasks, schedules, and workflow agent-task nodes can use portable
modelTierintent (smol,regular,smart,ultra), and operators can set per-agent reasoning effort (off→xhigh) without changing task payloads. Harness config → · Add a new provider → - OpenTelemetry traces plus OTLP cost/token metrics — export API + worker traces and finalized session cost/token counters through the same OTLP pipeline for dashboarding in SigNoz, Datadog, Tempo, or another compatible backend. Observability →
- Follow-up continuity across all harnesses — child tasks inherit a bounded prior-task context preamble built from the task chain, so continuity survives restarts and works the same across every provider. Task lifecycle →
- Skills & MCP servers — reusable procedural knowledge, bundled skill reference files, and per-agent MCP servers with scope cascade. MCP tools →
- External tool-router access — the
xcommand andswarm_xMCP tool let humans and agents execute approved third-party routes such as Composio without baking bespoke MCP servers first. CLI → · Composio → - Config-driven metrics dashboards — define read-only SQL widgets, version them, and render them in the dashboard without shipping custom frontend code. Metrics API →
- DB-backed pages — agents publish HTML or JSON pages (reports, dashboards, action specs) via the
create_pageMCP tool with public / authed / password modes, version history, view counters, diff helpers, and PDF export. MCP tools → Pages - KV store — Redis-like namespaced key/value store with auto-scoped context (Slack thread / PR / Linear issue / page). MCP tools → KV
- Real-time dashboard — monitor agents, tasks, and inter-agent chat. app.agent-swarm.dev →
Deployment
For production deployments (Docker Compose with multiple workers, systemd for the API, graceful shutdown, integration config), see DEPLOYMENT.md and the deployment guide.
Known Use Cases
Use cases that are used daily by ourselves and others. Each playbook contains: the agents, the tools & skills, and workflows & schedules behind it. Browse all playbooks →
- Feature Development — Integrated with Linear and GitHub to take feature requests from Slack and turn them into pull requests.
- Lead Prospecting — Integrate your prospecting tools with the swarm and let agents handle outreach, scheduling, and follow-up.
- Content Generation — Generate engagement tools, blog posts, manage social media presence, update your website, and more.
- UX Command Center — Agents that keep your product usable: record agentic sessions, enforce your design system, and mine user logs to detect and propose UX improvements.
- Proactive Customer Support — Agents that oversee your top accounts, prepare scheduled reports, and leverage everything they know about your platform to keep those accounts up to date.
- Code Health & Alert Management — Datadog, New Relic, Sentry, or any alerting tool can kick off fixes or new proposals. Monitor code health and propose improvements weekly, daily, or hourly.
- Reports from Multiple Sources — Integrate your data warehouse to generate tailored reports and answer the key questions your team has, with fresh data. Your BI tool may be a thing of the past.
- Self-Documenting & Release Reports — Update your docs and use frameworks like Remotion, qa-use, and browser-use to generate release videos and rich documentation in seconds, at the cadence you need.
- Do you have a cool playbook to share? Send us a PR!
The patterns that compound. Five recipes show up in nearly every playbook — they're how the swarm stays reliable as it scales: Litmus Tests (LLM-as-judge quality gates) · Drain Loops (one ticket → a chain of reviewable PRs) · HITL Gates (pause for human approval on irreversible steps) · Per-Customer Working Directories (context that compounds per account) · No-op Workflows (skip silently when nothing changed). See all patterns →
Check our templates for a quick start.
Quick Start
Need help? Contact us at contact@desplega.sh.
Prerequisites: Docker and at least one supported harness credential. The default quick start assumes a Claude Code OAuth token (claude setup-token), but pi-mono / Bedrock, Codex, Devin, and other provider setups are also supported.
The fastest way is the onboarding wizard — it collects credentials, picks presets, and generates a working docker-compose.yml:
bunx @desplega.ai/agent-swarm onboard
npx @desplega.ai/agent-swarm onboardPrefer manual setup? Clone and run with Docker Compose:
```bash git clone https://github.com/desplega-ai/agent-swarm.git cd agent-swarm cp .env.docker.example .env
edit .env — set API_KEY plus the credential for your chosen harness (for example CLAUDE_CODE_OAUTH_TOKEN)
docker compose -f docker-compose.example.yml --env-file .env up -d ```
The API runs on port 3013, with interactive docs at http://localhost:3013/docs and an OpenAPI 3.1 spec at http://localhost:3013/openapi.json.
<details> <summary><strong>Other setups</strong></summary>
- Local API + Docker workers — run the API on your host, workers in Docker. See Getting Started.
- Claude Code as the lead agent —
bunx @desplega.ai/agent-swarm connect(ornpx @desplega.ai/agent-swarm connect), then tell Claude Code to register as the lead.
</details>
[CLI](https://docs.agent-swarm.dev/docs/reference/cli)
bunx @desplega.ai/agent-swarm <command>
npx @desplega.ai/agent-swarm <command>| Command | Description |
|---|---|
onboard | Set up a new swarm from scratch (Docker Compose wizard) |
connect | Connect this project to an existing swarm |
api | Start the API + MCP HTTP server |
worker | Run a worker agent |
lead | Run a lead agent |
e2b | Build E2B templates and launch/manage grouped API + lead + worker swarms |
x | Execute approved external routes such as Composio |
docs | Open documentation (--open to launch in browser) |
Integrations
Missing one? Ask the swarm to build it.
| Integration | What it does | Setup |
|---|---|---|
| **Slack** | DM or @mention the bot to create tasks; workers reply in threads | [Guide](https://docs.agent-swarm.dev/docs/guides/slack-integration) |
| **GitHub App** | @mention or assign the bot on issues/PRs; CI failures create follow-up tasks | [Guide](https://docs.agent-swarm.dev/docs/guides/github-integration) |
| **GitLab** | Same model as GitHub — webhooks on issues/MRs, glab preinstalled in workers | [Guide](https://docs.agent-swarm.dev/docs/guides/gitlab-integration) |
| **AgentMail** | Give each agent an inbox; emails become tasks or lead messages | [Guide](https://docs.agent-swarm.dev/docs/guides/agentmail-integration) |
| **Kapso (WhatsApp)** | Native inbound WhatsApp webhook routing; agents reply over WhatsApp with MCP tools or the kapso-whatsapp skill | [Guide](https://docs.agent-swarm.dev/docs/integrations/kapso) |
| **Composio** | Route approved third-party app operations through agent-swarm x composio ... or the swarm_x MCP tool | [Guide](https://docs.agent-swarm.dev/docs/integrations/composio) |
| **Linear** | Bidirectional ticket sync via OAuth + webhooks | [Guide](https://docs.agent-swarm.dev/docs/guides/linear-integration) |
| **Jira Cloud** | OAuth 3LO ticket sync — assignee/comment events create tasks; lifecycle posts comments back | [Guide](https://docs.agent-swarm.dev/docs/guides/jira-integration) |
| **Sentry** | Workers can triage Sentry issues with the /investigate-sentry-issue command | [Guide](https://docs.agent-swarm.dev/docs/guides/sentry-integration) |
| **Devin** | Devin can be a node in your swarm — keep your existing configuration | [Guide](https://docs.agent-swarm.dev/docs/guides/harness-configuration#supported-providers) |
中文项目简介
本项目提供了多项功能，包括在 Docker 中的主从节点调度、隔离开发环境、优先队列、暂停和恢复部署等。它还支持 agent 记忆过去的会话并演化自己的个性、专长和笔记等功能。
环境依赖与系统要求中文说明
生产环境部署（使用 Docker Compose 和多个工作者、systemd 运行 API、优雅关闭、集成配置）请参见 DEPLOYMENT.md 和 部署指南。
配置说明（含 MCP / env / 关键参数）
API/接口说明
集成说明，包括 Slack 和 GitHub App 等
成熟的多代理框架，活跃维护中。Agent间协作设计优秀，Claude集成紧密，适合专业开发者构建复杂AI工作流系统。
- 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
- 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：agent-swarm 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
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 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
- 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
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
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。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
🔗 相关工具推荐
❓ 常见问题 FAQ
AI Skill Hub 点评：agent-swarm Agent工作流 的核心功能完整，质量优秀。对于AI爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | agent-swarm |
| 原始描述 | 开源AI工作流：Agent Swarm framework for AI coding agents and more!。⭐446 · TypeScript |
| Topics | 多代理系统Claude集成AI编码工作流编排TypeScript |
| GitHub | https://github.com/desplega-ai/agent-swarm |
| License | MIT |
| 语言 | TypeScript |
收录时间：2026-05-18 · 更新时间：2026-05-19 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。