mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 20:53:15 +00:00
49 lines
1.9 KiB
Text
49 lines
1.9 KiB
Text
---
|
|
title: "Introduction"
|
|
description: "How to use Open SWE"
|
|
---
|
|
|
|
# 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
|
|
|
|
<CardGroup cols={2}>
|
|
<Card title="Web Interface" icon="browser" href="/labs/swe/usage/ui">
|
|
Interactive chat interface with manual and auto modes for direct agent
|
|
communication
|
|
</Card>
|
|
<Card title="GitHub Webhooks" icon="webhook" href="/labs/swe/usage/github">
|
|
Automated triggers through GitHub issue labels for seamless repository
|
|
integration
|
|
</Card>
|
|
</CardGroup>
|
|
|
|
## Getting Started
|
|
|
|
### Try the Demo
|
|
|
|
You can explore Open SWE's capabilities using our hosted demo at [swe.langchain.com](https://swe.langchain.com).
|
|
|
|
<Note>
|
|
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](/labs/swe/setup/development).
|
|
</Note>
|
|
|
|
### 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?
|
|
|
|
<Tip>
|
|
Start with the [Web Interface guide](/labs/swe/usage/ui) to understand Open
|
|
SWE's core capabilities, then explore [GitHub
|
|
Webhooks](/labs/swe/usage/github) for automated integration into your
|
|
development workflow.
|
|
</Tip>
|
|
|
|
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.
|