Static Analysis meets Large Language Models
Semantic Crash Bucketing
Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol
AI-Powered Bug Diagnosis Agent with Experiential Memory — the more bugs it sees, the faster it gets.
A smart local proxy that fixes the “No Internet, Secured” error in Windows by safely emulating msftconnecttest.com and restoring real connectivity detection.
Code Buddy Assist is a tool that enhances your coding experience by integrating Large Language Models (LLMs) to provide comprehensive support, from high-level architecture decisions to detailed bug fixing. It creates project snapshots, enabling AI to understand your code context and offer tailored guidance and assistance.
AI-powered bug-fixing pipeline orchestrator — verification modules own stage transitions, not the LLM.
A reliability layer for AI-built systems: detect failures (tests or runtime drift), reproduce, repair one ticket at a time behind an approval gate, and prove the fix. The safety boundaries most AI agents skip.
PyPatch— OpenEnv RL environment where AI agents debug & fix buggy Python code across 3 difficulty levels.
Claude Code MCP native extension delivering a zero-human closed loop: Auto Bug Retrieval → Intelligent Troubleshooting → Automated Structured Accumulation. Equips Claude Code with long-term troubleshooting memory and establishes a reusable bug knowledge library for individuals and teams.
This project uses HTTP requests to connect with APIs or web servers for essential data tasks in data science workflows, including retrieval, submission, and updating. In this project, I utilize Python, HTML, and Flask frameworks to refactor and fix bugs identified for the Scribble app.
HAFix is an approach that leverages historical heuristics associated with bugs to enhance LLMs' bug-fixing capabilities
A bug fix repository that can test users coding skills as a replacement to Leetcode
Agent Teams Eval: comparing Claude Code Agent Teams vs subagents for bug-fixing on Ruff. Ceiling effect — 8/8 solve rate, zero peer communication.
Soft fix for Elite Suito speed bug.
An empirical study of bug-fixing patterns in open-source Python repositories.
Autonomous bug-fixing AI agent. Describe a bug and a pipeline of agents finds the root cause, writes a minimal fix, proves it with tests, and opens a pull request. Multi-language: Python, Java, C, C++, C#.
A test-first bug-fixing agent that proves its fixes against a held-out verifier the agent never sees.
CLI-based Automated Debugging Agent that detects runtime errors, applies fixes, and re-executes programs across multiple languages.
Vex - open-source AI coding agent that fixes real bugs end-to-end in a Docker sandbox, gates success on the repos own test suite, and routes model calls by predicted difficulty
To associate your repository with the bug-fixing topic, visit your repo's landing page and select "manage topics."