Skip to content
SPECIFICTION
Get listed

SWE-agent

swe-agent.com

WebWindowsmacOSLinuxSelf-hosted
Visit swe-agent.com
Spec score 7.9 #68 of 102 in AI Coding Assistants

Spec sheet

Purpose
SWE-agent uses language models to autonomously work on software engineering tasks, including fixing issues in GitHub repositories.Read 12 Oct 2026 · swe-agent.com
Platforms
The FAQ says SWE-agent runs on Windows, macOS, and Linux, with Docker environment availability as a possible limitation.Read 12 Oct 2026 · swe-agent.com
Support
The FAQ directs users to open GitHub issues for questions, bug reports, and feature requests, and links to Slack discussions.Read 12 Oct 2026 · swe-agent.com
Browser setup
SWE-agent can be run in a browser-based VS Code environment, where users provide language-model API keys in a .env file.Read 11 Oct 2026 · swe-agent.com
Browser use
The setup guide offers a browser-based VS Code environment for a quick first look and lists Node.js as a requirement for the web-based GUI.Read 12 Oct 2026 · swe-agent.com
Coding agent
YesRead 22 Sep 2026 · github.com
Configuration
The project describes itself as configurable through a YAML file and designed to be simple and hackable for research.Read 12 Oct 2026 · swe-agent.com
Credentials
Users supply their own language-model keys and need a GitHub key to access private repositories.Read 12 Oct 2026 · swe-agent.com
Current recommendation
The maintainers recommend mini-swe-agent, which they say matches SWE-agent’s performance while being simpler.Read 11 Oct 2026 · swe-agent.com
Customization
Users can add custom tools and change the demonstration trajectory supplied to the agent at the start of each run.Read 12 Oct 2026 · swe-agent.com
Image support
The documentation describes multimodal support for processing images from GitHub issues and says images must be under 10 MB.Read 11 Oct 2026 · swe-agent.com
Images
SWE-agent supports vision-capable models for processing images from GitHub issues, and the FAQ says images must be under 10 MB.Read 12 Oct 2026 · swe-agent.com
Installation
The preferred setup is installation from source using pip.Read 11 Oct 2026 · swe-agent.com
Local model limits
For local models, the documentation says cost tracking cannot be used unless a custom model registry supplies cost information.Read 11 Oct 2026 · swe-agent.com
Model support
The documentation says SWE-agent supports models available through LiteLLM and local models served through an OpenAI-compatible API.Read 11 Oct 2026 · swe-agent.com
Models
The documentation says SWE-agent supports models served through LiteLLM and local models with an OpenAI-compatible API.Read 12 Oct 2026 · swe-agent.com
Operating systems
The FAQ says SWE-agent runs on Windows, macOS, and Linux, with Docker container availability possibly limiting environment choices.Read 11 Oct 2026 · swe-agent.com
Project status
The documentation says SWE-agent has been superseded by mini-swe-agent and is now in maintenance-only mode.Read 12 Oct 2026 · swe-agent.com
Research design
Its Agent-Computer Interface provides commands and feedback for models to browse repositories, view and edit files, and run code.Read 12 Oct 2026 · swe-agent.com
Research focus
The project describes itself as made for research and simple and hackable by design.Read 11 Oct 2026 · swe-agent.com
Run records
The FAQ says `.traj` output files contain complete records of SWE-agent's thought process and actions.Read 12 Oct 2026 · swe-agent.com
Runtime
Docker is the default backend; the documentation says cloud code evaluation is an option for users who do not want to use Docker.Read 12 Oct 2026 · swe-agent.com
Status
SWE-agent has been superseded by mini-swe-agent and is now in maintenance-only mode.Read 11 Oct 2026 · swe-agent.com
Terminal access
YesRead 22 Sep 2026 · github.com

Where Specifiction places it

Alternatives to SWE-agentAll alternatives →