DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。​让安全不再昂贵，让审计不再复杂。

Detect concurrency and memory bugs and possible panic locations in Rust projects

A Tool for clone detection and bug detection in smart contracts

No description provided.

An automatic API misuse checker for C programs!

OpenClaw skill: Dynamic bug audit for Node.js web projects (games, data tools, WeChat, APIs, bots). 200+ real-world pitfalls.

No description provided.

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

Bug detection and fixing using prompt engineering and fine-tuning with Llama 3 and a custom mutation-based dataset. Includes a user-friendly interface and performance evaluation metrics.

Code of our paper "Method-Level Bug Severity Prediction using Source Code Metrics and LLMs" which is accepted to ISSRE 2023.

Bug detection and repair algorithm

Prevent memory leaks and runtime crashes in .NET Dependency Injection. A zero-overhead Roslyn analyzer that catches captive dependencies, undisposed scopes, and lifetime mismatches at compile-time.

🤖 Simplify code reviews with XCodeReviewer, your smart partner for efficient and effective code audits in any development project.

Deep learning-based bug detector for IntelliJ

Bug detectors for Golang

Deep learning project to detect logic bugs in source code.

A graph based bug classifier using the dgl library and DeepBugs dataset

Python package to predict bugs using the complexity of code changes

Generate more realistic mutations with contextual mutants

An attempt at detecting SStuBs using a pre-trained transformer and repairing them with a seq2seq model.

🤖 基于 MCP 协议的 MUD 游戏自动化测试与智能修复工具 | AI-powered MUD game testing & auto-repair tool based on MCP protocol

The AI Developer's Assistant aims to enhance developer productivity by analyzing code snippets, identifying bugs, suggesting optimizations, generating unit tests, and debugging log files.

🔍 Three-tier code quality defense for AI agents: L1 quick scan, L2 deep audit, L3 cross-validation with adversarial testing. OpenClaw Agent Skill.

Machine Learning Project for Bug Detection in Python using traditional machine learning algorithms

An AI-powered agent that automatically detects, explains, and fixes issues in AI-generated or human-written code — from syntax errors to security flaws — with safe, test-backed patches.

This project uses Natural Language Processing (NLP) and Machine Learning techniques to analyze user reviews of top-selling games on the Steam platform. The goal is to detect bug-related reviews using keyword filtering, assess user sentiment (positive, neutral, negative), and group similar games using clustering methods.

🔍 Prevent memory leaks and `ObjectDisposedException` with compile-time analysis tools that ensure proper Dependency Injection lifetimes in your applications.

TestPilot is a production-grade Chrome extension that captures crashes, console errors, network failures, security risks, slow APIs, retry storms, and broken resources before users report them. Built with Preact + TypeScript + Vite.

Collaborative AI triage for code, plans and architecture — Claude, Gemini and Codex independently analyze then merge findings with consensus scoring. Security audits, bug hunts, plan reviews, second opinions. Claude Code skill + MCP server.

Detect variable shadowing in JavaScript/TypeScript code to catch subtle bugs from redefined variables