Project page for "The Debugging Book"

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.

A CLI and MCP server for Java codebase graph indexing, call tracing, and LLM-assisted diagnosis. Builds a static call graph via tree-sitter, traces method and route flows, generates deterministic flow and error investigation docs, and benchmarks 69–80% context reduction vs baseline LLM exploration.

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

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.

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.

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

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