Swarm编排器 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。
Swarm编排器 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。
Swarm编排器 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。
# 方式一:npm 全局安装 npm install -g swarm-orchestrator # 方式二:npx 直接运行(无需安装) npx swarm-orchestrator --help # 方式三:项目依赖安装 npm install swarm-orchestrator # 方式四:从源码运行 git clone https://github.com/moonrunnerkc/swarm-orchestrator cd swarm-orchestrator npm install npm start
# 命令行使用
swarm-orchestrator --help
# 基本用法
swarm-orchestrator [options] <input>
# Node.js 代码中使用
const swarm_orchestrator = require('swarm-orchestrator');
const result = await swarm_orchestrator.run(options);
console.log(result);
# swarm-orchestrator 配置说明 # 查看配置选项 swarm-orchestrator --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 SWARM_ORCHESTRATOR_CONFIG="/path/to/config.yml"
<a id="readme-top"></a>
<p><strong>A proof-carrying runner and verifier for bounded code changes.</strong></p>
<p> The model can say whatever it likes.<br /> It cannot make a gate pass, mark a claim verified, or change a record after the fact. </p>
<p> <a href="docs/README.md"><strong>Explore the docs »</strong></a> <br /> <br /> <a href="docs/evidence/2026-08-18/live-tasks.md">See a real run</a> · <a href="https://github.com/moonrunnerkc/swarm-orchestrator/issues/new?labels=bug">Report Bug</a> · <a href="https://github.com/moonrunnerkc/swarm-orchestrator/issues/new?labels=enhancement">Request Feature</a> </p>
</div>
---
<details> <summary><strong>Table of Contents</strong></summary> <ol> <li><a href="#about-the-project">About The Project</a></li> <li><a href="#built-with">Built With</a></li> <li><a href="#getting-started">Getting Started</a></li> <li><a href="#usage">Usage</a></li> <li><a href="#what-it-reports">What it reports</a></li> <li><a href="#the-evidence">The evidence</a></li> <li><a href="#what-is-not-claimed">What is not claimed</a></li> <li><a href="#roadmap">Roadmap</a></li> <li><a href="#contributing">Contributing</a></li> <li><a href="#license">License</a></li> <li><a href="#contact">Contact</a></li> </ol> </details>
Give it a task and a git repository and it will make the change. Give it somebody else's patch and it will tell you what that patch actually establishes. Either way what comes back is a signed, hash-chained record of what ran, what passed, and what nobody measured — which anybody can check without installing this tool.
| **Make a bounded change** | It declares the files it intends to touch, edits through a chokepoint that records every tool call, runs your gates, and retries failures under a numeric ratchet that refuses a fix trading away tests, assertions or coverage. |
| **Verify anybody's patch** | swarm ci clones the base commit somewhere the producing tree cannot reach, applies the patch there, and runs the checks in that checkout. Nothing the producer said travels except the patch. |
| **Say what a result does not establish** | A run reports nine answers rather than a boolean, and unmeasured is one of the values. "Nobody checked" and "checked and failed" are different findings, and flattening them is how a change nothing executed comes to read green. |
Node 24 or newer. A runtime floor rather than a preference: the coverage cycle spawns the test runner with --test-isolation=process, which Node 22 rejects as a bad option, so on anything older that measurement does not happen.
A model, frontier or local:
```sh export ANTHROPIC_API_KEY=... # or OPENAI_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY
npm install -g swarm-orchestrator
That is 14.0.2, and it leaves swarm on your path. If swarm turns out to be an older version than you installed, swarm doctor says what owns the command and --fix repairs it.
Anything below 13 is a different program: this package name carried a pull-request auditor through 12.x. Pin the major if you depend on one or the other.
<p align="right">(<a href="#readme-top">back to top</a>)</p>
swarm "make slugify collapse whitespace and strip punctuation"
Real output, swarm gates over a two-test project:
passed tests: 2 collected, 2 passed, 0 failed, 0 skipped (exit 0)
passed placeholder: no placeholder marker was introduced by this change
passed secret-scan: no known credential pattern appears in the added lines
n/a typecheck: package.json declares no typecheck script
bonds, one per gate that passed:
tests: held. the tests gate refused the bond: 3 collected, 2 passed, 1 failed, 0 skipped
secret-scan: held. the secret-scan gate refused the bond: 1 added line(s) match a known
credential pattern: swarm-falsification-bond.env.example.js:1 (github-token)
acceptable: yes (no blocking gate failed, no policy gate failed, and something executed the change)
A pass is a claim until it is shown able to fail. After the gates go green, each one that passed is handed a bond — one file it has to refuse. A check that refused it held. A check that passed over a bond it demonstrably saw is vacuous, and a vacuous blocking gate makes the run not green whatever the cycle said.
The four commands most people need:
swarm # a session: type tasks, one after another
swarm gates # run the gates over a workspace, no model
swarm ci --patch <file> # verify a patch in a fresh checkout of the base
swarm verify <bundle> --signer <f> # check a bundle, and who signed it
Every command and flag is in docs/cli.md. Sessions, several workers at once and swarm.toml are in docs/using.md.
<p align="right">(<a href="#readme-top">back to top</a>)</p>
```
Keys come from the environment or your OS keychain, never from swarm.toml — that file is committed and cloned, so a key in it has already been shared with everyone holding the repository.
创新的AI智能体监管工具,针对性强。通过自动化审计机制提升代码安全性,对AI编码生态具有重要意义。维护活跃度良好。
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。
✅ ISC 协议 — 功能等同于 BSD 2-Clause,可自由商用,无额外限制。
经综合评估,Swarm编排器 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 | swarm-orchestrator |
| 原始描述 | 开源AI工作流:Audits pull-request diffs for 10 categories of AI-coding-agent cheat patterns; n。⭐92 · TypeScript |
| Topics | 工作流AI智能体代码审计Anthropic欺骗检测 |
| GitHub | https://github.com/moonrunnerkc/swarm-orchestrator |
| License | ISC |
| 语言 | TypeScript |
收录时间:2026-05-24 · 更新时间:2026-05-30 · License:ISC · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端