AI AGENTS

Open SWE

by LangChain

agentsubagents

Overview

Open-source asynchronous coding agent framework for internal engineering agents with sandboxes, Slack/Linear/GitHub triggers, subagents, and PR creation.

Details

Open SWE is a LangChain GitHub project described as an open-source asynchronous coding agent framework for internal engineering agents. The supplied repository metadata highlights support for sandboxes, Slack, Linear, and GitHub triggers, subagents, and pull request creation. The provided documentation URL points to an INSTALLATION.md file for setup information.

When to Use

Use Open SWE when evaluating an open-source asynchronous coding agent framework for internal engineering workflows. Consider it when you need coding-agent workflows that can be triggered from Slack Linear or GitHub and can create pull requests. Review it when sandboxed execution and subagent-based coding workflows are important requirements.

Getting Started

Open the GitHub repository at https://github.com/langchain-ai/open-swe.
Review the installation documentation at https://github.com/langchain-ai/open-swe/blob/main/INSTALLATION.md.
Inspect the repository contents and setup instructions before testing Open SWE in an internal engineering workflow.

Key Features

•Open-source asynchronous coding agent framework
•Designed for internal engineering agents
•Sandbox support
•Slack
•Linear
•and GitHub triggers
•Subagent support
•Pull request creation

Capabilities

•asynchronous coding agent workflows
•sandboxed agent execution
•Slack-triggered workflows
•Linear-triggered workflows
•GitHub-triggered workflows
•pull request creation

Last updated Jun 19, 2026