SWE-agent Review — Self-Hosted AI Tool
Unser Test von SWE-agent — Funktionen, Stärken und Schwächen.
SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4) to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform any custom task. Built by researchers from Princeton University and Stanford University, it achieves state-of-the-art results on SWE-bench among open-source projects. It features a flexible configuration system, Docker-based sandboxing, and supports multiple LLM backends including OpenAI, Anthropic, and open-source models.