SWE-agent
Open-source agent development and engineering for software engineering, issue resolution, code agent.
What does this agent do, and when should you use it?
The repository describes SWE-agent as: SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]. This profile is a source-based catalog entry; an independent FARS review is still pending.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024].
- Evaluate it for an agent application or engineering workflow.
- Prototype integrations around its documented tools or APIs.
- Inspect the source before adapting it to an existing stack.
What are this agent's strengths and limitations?
- Public source and README are available for inspection.
- Focused on software engineering, issue resolution, code agent.
- Setup, model-provider support, and maturity must be confirmed against the current release.
- No independent FARS score has been assigned yet.
How do you install or deploy this agent?
Follow the current installation instructions in the [repository README](https://github.com/SWE-agent/SWE-agent#readme). Requirements and provider setup vary by release.
How do you use this agent?
Start with the examples and quickstart in the [repository documentation](https://github.com/SWE-agent/SWE-agent#readme), then test the workflow with limited permissions and non-sensitive data.