AutoCodeRover
What it is
AutoCodeRover is an autonomous software engineering agent that resolves GitHub issues by combining LLMs with program structure-aware code search and statistical fault localization. It operates in two stages: retrieving relevant context from the abstract syntax tree and generating patches, achieving high efficacy on SWE-bench benchmarks at a low cost per task.
The problem it solves
Manual software debugging and patch generation are time-consuming and expensive, especially in large, complex codebases where locating the correct fix location is difficult.
What you could use it for
- Automatically fixing bugs in open-source repositories
- Implementing feature requests from GitHub issues
- Performing statistical fault localization in large codebases
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.