SWE-Agent Integration

SWE-agent is an AI-powered software engineering agent that can autonomously resolve GitHub issues by navigating codebases, editing files, and running tests. It uses language models to understand code and plan solutions.

SWE-agent supports custom model endpoints through its configuration, letting you connect LLM API.

Prerequisites

An LLM API account with an API key
SWE-Agent installed or accessible

Setup

Get Your LLM API Key

Log in to your LLM API dashboard
Click Create Key to Start
Copy your new API key immediately — it will only be shown once
Store the key securely (e.g., in a password manager or .env file)

LLM API is an OpenAI-compatible gateway that gives you access to dozens of AI models through a single API key and endpoint.

Configure LLM API in SWE-agent

Set environment variables:

export OPENAI_API_KEY="your-llm-api-key-here"
export OPENAI_BASE_URL="https://api.llmapi.ai/v1"

Or configure in the SWE-agent config file:

model:
name: openai/gpt-4o
api_key: your-llm-api-key-here
api_base: https://api.llmapi.ai/v1

Run SWE-agent as usual --- it will use LLM API.

Test the Integration

Verify that SWE-Agent can successfully communicate with LLM API by sending a test request. All requests will now be routed through LLM API.

SWE-agent benefits from strong reasoning models. Use LLM API to access the latest model offerings.

Benefits of Using LLM API with SWE-Agent

Multi-Provider Access: Use models from OpenAI, Anthropic, Google, and more through a single API
Cost Control: Track and limit your AI spending with detailed usage analytics
Unified Billing: One account for all providers instead of managing multiple API keys
Caching: Reduce costs with response caching for repeated requests

View all available models on the models page.