TTableAI Catalog

agent + benchmark

SWE-agent

A research system that enables language models to resolve software engineering tasks in repositories.

Visit projectView source

What it is

SWE-agent supplies an agent-computer interface and evaluation workflow for issue-driven software engineering experiments.

Related records

OpenAI CodexA coding agent for software development tasks across local tools, repositories, and cloud workflows.Claude CodeAn agentic coding tool that works from the terminal and integrates with development workflows.AiderAn open-source pair programming agent designed to edit code in local Git repositories.ClineAn open-source coding agent that operates inside Visual Studio Code with user-approved tool actions.