Project page for "The Debugging Book"

基于 AI Agent 服务自动化修复系统：Agent 自动读取错误日志，定位 Bug，生成补丁，运行测试，提交 PR，并通知开发者 Review。AI-powered auto-fix agent for web services: analyzes logs, patches code, runs tests, and creates pull requests automatically.

BigDebug: Debugging Primitives for Interactive Big Data Processing in Spark (ICSE 2016)

An experimental toolkit that transforms natural language prompts into production-ready Python applications. Features automated coding, testing, debugging, and documentation generation using DeepSeek AI. Supports both single-process and parallel multi-process execution for efficient solution discovery.

Framework-aware code intelligence for LLM agents. Indexes Java, Python, TypeScript, Go, Scala into a verified call graph via tree-sitter + Rust. MCP server, Haiku sub-agent, and git hooks included. 68–95% agent token reduction.

A multi-agent system that navigates ML repositories, reproduces reported results, and repairs failures in isolated environments.

Source code for the Klyve Software Development Factory.

Autonomous AI Code Repair Agent. Finds crashes, compiles code, and fixes bugs in real-time for Python, Rust, Go, & C++.

A multi-agent forensic audit engine for Infineon SmartRDI hardware code using LangGraph. Features an adversarial "Critic Layer" for hallucination-free bug detection, automated C++ remediation, and GTest generation.

Autonomous AI agent that writes, executes, debugs, and tests Python & SQL code — built with LangGraph, Groq, and LangChain. Zero manual intervention.

Influence-Based Provenance for Dataflow Applications with Taint Propagation (SoCC 2020)

CLI-based Automated Debugging Agent that detects runtime errors, applies fixes, and re-executes programs across multiple languages.

Automated Debugging in Data-Intensive Scalable Computing (SoCC 2017)

This repository contains exercises from CISPA Helmholtz Center for Information Security to implement a debugger from scratch using Python.