YerbaPage/SWE-Debate

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution

35
/ 100
Emerging

This helps software developers quickly pinpoint the exact code locations responsible for a reported bug or issue. It takes an issue description as input and uses an AI-powered debate process among virtual agents to identify relevant code entities, dependency paths, and ultimately, generates a detailed plan for code modifications. Software engineers and QA teams can use this to streamline their debugging and problem-solving workflows.

Use this if you need an automated, robust way to find the root cause and generate potential fixes for software issues within a large codebase.

Not ideal if you are working with small, simple scripts or require a purely manual, human-driven debugging process.

software-debugging issue-resolution code-maintenance software-engineering bug-localization
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Python

License

Apache-2.0

Category

ai-debate-arenas

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/YerbaPage/SWE-Debate"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.