---
name: "Run asynchronous coding-agent workflows with Open SWE"
slug: "run-asynchronous-coding-agent-workflows-with-open-swe"
description: "Deploy an internal coding agent that accepts tasks from GitHub, Slack, or Linear, runs them in isolated sandboxes, and opens pull requests automatically."
github_stars: 9823
verification: "security_reviewed"
source: "https://github.com/langchain-ai/open-swe"
author: "LangChain"
publisher_type: "organization"
category: "Developer Tools"
framework: "Custom Agents"
tool_ecosystem:
  github_repo: "langchain-ai/open-swe"
  github_stars: 9823
---

# Run asynchronous coding-agent workflows with Open SWE

Deploy an internal coding agent that accepts tasks from GitHub, Slack, or Linear, runs them in isolated sandboxes, and opens pull requests automatically.

## Prerequisites

Python, uv, GitHub App, LangSmith, sandbox provider, GitHub/Slack/Linear trigger

## Installation

Basic usage or getting-started notes:
- **[Installation Guide](INSTALLATION.md)** — GitHub App creation, LangSmith, Linear/Slack/GitHub triggers, and production deployment
- **[Customization Guide](CUSTOMIZATION.md)** — swap the sandbox, model, tools, triggers, system prompt, and middleware for your org
- ## License

- Source: https://github.com/langchain-ai/open-swe
- Extracted from upstream docs: https://raw.githubusercontent.com/langchain-ai/open-swe/HEAD/README.md

## Documentation

- https://openswe.vercel.app

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-asynchronous-coding-agent-workflows-with-open-swe/)