Augment SWE-bench Verified Agent
What it is
An open-source implementation of a coding agent designed to solve SWE-bench Verified tasks, utilizing Claude Sonnet 3.7 as the core driver and OpenAI o1 for ensembling. It provides a Docker-based harness, interactive CLI, and evaluation scripts to navigate codebases and fix issues.
The problem it solves
Lack of a simple, open-source, and high-performing implementation for SWE-bench that leverages current state-of-the-art models for complex codebase navigation and regression testing.
What you could use it for
- Evaluating LLM performance on real-world software engineering tasks
- Automating the resolution of GitHub issues in open-source projects
- Experimenting with agentic coding workflows using off-the-shelf models
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.