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。

An automatic API misuse checker for C programs!

Python package to predict bugs using the complexity of code changes

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

Generate more realistic mutations with contextual mutants

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

Self-supervising TLA+ formal verification loop — an LLM agent iteratively writes specs and fixes bugs, using the TLC model checker as an incorruptible evaluator. Inspired by Karpathy's autoresearch.

🤖 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

FailMapper: Failure-Scenario-Guided Unit Test Generation using Monte Carlo Tree Search (MCTS) and LLMs. Detects 233% more bugs than baselines on Defects4J. Covers 9 failure scenarios for automated bug detection in Java programs. [ASE 2025]

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.

NLP-based code interpreter that detects language, explains, translates, optimizes code using Tokenization, TF-IDF, Stemming & Lemmatization, analyzes complexity & detects bugs — built with Python, Streamlit & Groq API

AI Code Review Memory - learns from your team's bug history and warns when similar patterns appear

Multi-agent beta testing framework where LLaVA vision agents form committees to test web apps. Agents analyze screenshots, discuss actions, vote on consensus, and catch bugs + security vulnerabilities. Playwright browser automation, Streamlit dashboard, FastAPI backend.

Web-based benchmark suite that evaluates how well LLMs catch real-world concurrency bugs, deadlocks, and distributed systems edge cases. Includes automated 1–20 scoring via LLM judge, side-by-side run comparisons, and support for local (Ollama) and cloud providers.

Desktop GUI tool that scans Ren'Py visual novel projects for bugs and generates styled PDF reports

AI-powered catching test generator — finds bugs before code review. First open-source implementation of Meta's JiTTests (FSE 2026).