​
Using Open SWE

Open SWE provides two primary ways to interact with the coding agent, each designed for different workflows and use cases. Whether you prefer direct interaction through a web interface or automated triggers through GitHub webhooks, Open SWE adapts to your development process.

​
Usage Methods

Web Interface

Interactive chat interface with manual and auto modes for direct agent communication

GitHub Webhooks

Automated triggers through GitHub issue labels for seamless repository integration

​
Getting Started

​
Try the Demo

You can explore Open SWE’s capabilities using our hosted demo at swe.langchain.com.
The demo application requires you to provide your own LLM API keys. For production use or development, we recommend setting up your own instance following our development setup guide.

​
Choose Your Workflow

  • Web Interface: Best for interactive development, experimentation, and when you want direct control over the agent’s planning and execution process
  • GitHub Webhooks: Ideal for automated workflows, issue-driven development, and team collaboration where coding tasks are tracked through GitHub issues

​
What’s Next?

Start with the Web Interface guide to understand Open SWE’s core capabilities, then explore GitHub Webhooks for automated integration into your development workflow.
Both usage methods leverage the same underlying LangGraph agent architecture with specialized graphs for planning, programming, and management, ensuring consistent behavior regardless of how you interact with Open SWE.