# Open SWE — Async Coding Agent from LangChain

> Open SWE is LangChain's open-source asynchronous coding agent. It connects GitHub app workflows, LangSmith tracing, triggers, sandboxes, and review loops.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

1. Install the verified package or repo entrypoint:

```bash
git clone https://github.com/langchain-ai/open-swe
cd open-swe
```

2. Run the first local check:

```bash
Follow INSTALLATION.md for GitHub App, LangSmith, triggers, and sandbox setup.
```

3. Add a repeatable verification command:

```bash
npm test || pnpm test
```

---

## Intro

Open SWE is a verified GitHub-backed tool for modern AI and developer workflows, sourced from `langchain-ai/open-swe` with 9,773 stars and a MIT license snapshot. Best for: teams evaluating asynchronous coding agents that operate from GitHub issues, Linear tickets, Slack triggers, or sandboxed workspaces. Works with: GitHub Apps, LangSmith, Linear or Slack triggers, sandbox providers, customizable middleware. Setup time: 25 minutes. Use it when you need a concrete, repeatable path rather than another one-off shell snippet.

---

## Operating Pattern

### Fit check

| Question | Practical answer |
|---|---|
| What do you install? | `open-swe` from `langchain-ai/open-swe` |
| What is the first command? | `Follow INSTALLATION.md for GitHub App, LangSmith, triggers, and sandbox setup.` |
| What proves it works? | `npm test || pnpm test` |
| How long should a pilot take? | 25 minutes for a small repo or sandbox |

### Adoption loop

1. Run the tool on a disposable branch or sandbox project.
2. Capture before/after output so reviewers can see the exact effect.
3. Add the smallest CI or local check that prevents regressions.
4. Document owner, upgrade command, and rollback command in the repo.

### Recommended use

Use it as an architecture reference even before rollout: inspect how triggers, sandboxes, tracing, and review loops connect around a long-running coding task.

### Guardrails

Budget setup time for GitHub App permissions and sandbox policy. This is a system integration, not a one-command CLI install.

### Rollout checklist

- Pin the package or release version before using it in CI.
- Keep credentials in environment variables or the platform secret store.
- Add one owner who is responsible for upgrades and breaking-change triage.
- Re-check the GitHub repo before writing docs that mention APIs or install paths.


---

### FAQ

**Q: Is this production-ready?**
A: The repo exists at `https://github.com/langchain-ai/open-swe` and has 9,773 GitHub stars. Treat the first rollout as a controlled pilot until your team has tested install, rollback, and CI behavior.

**Q: Why use it instead of a generic script?**
A: The value is repeatability: a named package, a documented command, a source repo, and a small verification path that can be reviewed by teammates.

**Q: What should I measure first?**
A: Measure setup time against the 25 minutes target, count how many files or tasks it changes, and record whether the CI command catches the same issue locally.

---

## Source & Thanks

> Built from [langchain-ai/open-swe](https://github.com/langchain-ai/open-swe). License: MIT.
>
> GitHub stars verified from `api.github.com/repos/langchain-ai/open-swe`: 9,773.

---

<!-- ZH -->

## 快速使用

1. 安装已验证的包或仓库入口：

```bash
git clone https://github.com/langchain-ai/open-swe
cd open-swe
```

2. 跑第一次本地检查：

```bash
Follow INSTALLATION.md for GitHub App, LangSmith, triggers, and sandbox setup.
```

3. 加一个可重复验证命令：

```bash
npm test || pnpm test
```

---

## 简介

Open SWE 是一个已通过 GitHub 仓库验证的现代 AI / 开发者工具，来源 `langchain-ai/open-swe`，当前星标快照 9,773，许可证 MIT。适合：评估异步 coding agent 的团队，尤其是从 GitHub issue、Linear ticket、Slack 触发或 sandbox 工作区启动的场景。兼容：GitHub App、LangSmith、Linear 或 Slack 触发器、sandbox provider、自定义 middleware。装机时间：25 minutes。当你需要的是可重复落地路径，而不是一次性 shell 片段时，用它。

---

## 操作模式

### 适配检查

| 问题 | 实用答案 |
|---|---|
| 安装什么？ | 来自 `langchain-ai/open-swe` 的 `open-swe` |
| 第一条命令？ | `Follow INSTALLATION.md for GitHub App, LangSmith, triggers, and sandbox setup.` |
| 如何证明可用？ | `npm test || pnpm test` |
| 小范围试点多久？ | 小仓库或 sandbox 约 25 minutes |

### 接入循环

1. 先在一次性分支或 sandbox 项目里跑。
2. 记录 before / after 输出，让 reviewer 看见实际影响。
3. 加最小的 CI 或本地检查，防止同类问题回归。
4. 在仓库文档里写清 owner、升级命令和回滚命令。

### 推荐用法

即使还不上线，也可以把它当架构参考：观察触发器、sandbox、tracing 和 review loop 如何围绕长时间 coding task 连接。

### 风险边界

为 GitHub App 权限和 sandbox 策略预留配置时间。它是系统集成，不是一条命令安装的 CLI。

### 推广检查表

- 进入 CI 前固定包版本或 release 版本。
- 凭据放进环境变量或平台 secret store。
- 指定一个 owner 负责升级和 breaking change 分流。
- 文档里写 API 或安装路径前，重新核验 GitHub 仓库。


---

### FAQ

**Q: 能直接上生产吗？**
A: 仓库已验证存在：`https://github.com/langchain-ai/open-swe`，GitHub 星标 9,773。第一次上线仍建议控制试点，先验证安装、回滚和 CI 行为。

**Q: 为什么不用普通脚本？**
A: 价值在可重复：有命名包、文档化命令、源仓库和可被团队 review 的最小验证路径。

**Q: 第一步应该量什么？**
A: 先量装机时间是否接近 25 minutes，它改了多少文件或任务，以及 CI 命令是否能在本地抓到同类问题。

---

## 来源与感谢

> 来源：[langchain-ai/open-swe](https://github.com/langchain-ai/open-swe)。许可证：MIT。
>
> GitHub stars 已通过 `api.github.com/repos/langchain-ai/open-swe` 验证：9,773。


---
Source: https://tokrepo.com/en/workflows/open-swe-async-coding-agent-from-langchain
Author: LangChain AI