Graphify builds queryable knowledge graphs from codebases using local tree-sitter parsing for code and LLMs for docs, enabling AI assistants to traverse real code relationships via query, path, and explain commands, with benchmark results showing 0.497 recall@10 on LOCOMO versus 0.048 for mem0.
Archify is an AI agent skill that analyzes code repositories to produce validated, interactive architecture diagrams in five types — Architecture, Workflow, Sequence, Data Flow, and Lifecycle — with a rigorous JSON Schema and layout validation pipeline, an interactive HTML viewer supporting search, path tracing, role comparison, and Architecture Delta for PR diffing, all delivered as a single shareable HTML file.
Graft builds a local Markdown knowledge graph for AI coding agents, replacing embedding-based retrieval with deterministic structural analysis and optional LLM semantic layers, auto-refreshing on each query to cut token usage by 42% and improve SWE-bench scores by 12 percentage points.
This article introduces codebase-memory-mcp, an MCP-based tool that indexes entire codebases into a queryable knowledge graph, enabling AI coding assistants to understand module call relationships, perform impact analysis, and answer structural queries via openCypher across 158 languages.
This tutorial explains how to install Graphify, generate a local knowledge graph of an entire codebase—including code, docs, PDFs, images, and videos—and then query the graph via AI assistants or the CLI, eliminating the need for manual full‑text file searches.
The article explains how Coding is evolving from a traditional code‑hosting platform to a comprehensive AI‑powered development ecosystem, detailing a three‑layer AI infrastructure, remote agent frameworks, front‑end integration points, and multiple real‑world cases that showcase AI‑driven code understanding, automated fixes, release checks, alert remediation, SQL review, knowledge consolidation, and testing automation.
Java developers often dread taking over an undocumented, multi‑module Spring Boot system, but by using Claude Code for read‑only analysis you can generate a module map, risk report, live documentation and a step‑by‑step migration plan before touching any code.
CodeGraph is an open‑source AI‑powered code‑graph tool that builds a local SQLite knowledge graph of all symbols, calls and dependencies across more than 20 languages, enabling agents to retrieve complete call chains and impact analysis with a single query, dramatically cutting traversal overhead for large projects.
New developers often drown in massive legacy codebases, struggling to map dependencies and understand architecture, but Understand‑Anything leverages Claude, Tree‑sitter, and multi‑agent pipelines to generate a searchable, visual knowledge graph, offering onboarding tours, semantic QA, incremental diff analysis, and cross‑language support, while the article also compares it against competing tools and provides installation and usage guidance.
Graphify is a Python tool and Claude Code skill that creates a persistent, queryable knowledge graph of code, documentation, and media, cutting token usage by up to 71.5× compared with raw file reads, and it does so through a three‑pass pipeline that combines deterministic AST extraction, optional local audio transcription, and AI‑driven semantic extraction.
Understand‑Anything is a Claude Code plugin that uses a multi‑agent pipeline to turn large, unfamiliar codebases into searchable, interactive knowledge graphs, supporting nine AI coding tools, offering visual dashboards, natural‑language Q&A, incremental diff, and detailed onboarding while noting token costs and large‑graph performance limits.
GitNexus is an open‑source tool that indexes any code repository into a searchable knowledge graph, enabling AI agents to understand code structure through a CLI‑MCP mode or a web UI, and it differentiates itself from DeepWiki by focusing on deep structural analysis and tool‑use hooks.
This guide walks through building a production‑grade code‑analysis assistant, detailing requirements, architecture, a Node.js tech stack, TF‑IDF RAG implementation, dynamic skill loading, secure tool calls, memory handling, observability, common pitfalls, and paths to scale from a demo to a full‑featured system.
Graphify is a Python tool that parses codebases into a searchable knowledge graph, eliminating the need for costly vector retrieval by traversing explicit entity‑relationship graphs, achieving up to 71.5× token reduction, supporting AST extraction, optional local audio transcription, and AI‑driven semantic extraction with confidence labeling.
The article introduces the open‑source tool Understand Anything, explains how it combines Claude Code’s LLM with static code analysis to turn any codebase into an interactive, searchable knowledge graph, and walks through a full installation and usage demo on a Java e‑commerce project.
When inheriting a Spring Boot project with hundreds of thousands of lines and no documentation, the article shows how to leverage Claude to map module boundaries, extract business flows, classify responsibilities, generate architecture diagrams, and guide bulk refactoring, turning unreadable code into a clear structural view.
Claude's new 1‑million‑token context window is now generally available at the same price as the 200K tier, unlocking full‑project analysis, faster refactoring, and cheaper large‑scale usage compared with Gemini and GPT, while outlining practical tips and pitfalls.
This tutorial introduces LangChain4j's new Agent Skills feature, explains its core concepts, and walks through a complete example of creating a reusable code‑analysis skill in Java, covering dependency setup, skill definition, integration, and expected runtime behavior.
GitNexus is an open‑source knowledge‑graph tool that indexes an entire codebase, exposing dependencies and call chains so AI assistants can understand global architecture, instantly show impact of changes, and dramatically reduce the risk of introducing new bugs during development.
Anthropic's new Claude Code Security tool uses an AI model that reads code like a human researcher, detecting complex logic‑flaw and permission‑control bugs missed by traditional pattern‑matching scanners, providing multi‑round verification, confidence scores, and AI‑generated patches while still requiring developer approval.
Anthropic’s limited‑preview Claude Code Security, an AI agent that reads and patches code, triggered a sharp sell‑off in major cybersecurity stocks, while its ability to uncover hundreds of hidden bugs raises questions about the future role of traditional security firms and junior analysts.
The article evaluates Anthropic's Claude Sonnet 4.6 as a comprehensive research assistant, detailing its performance on literature surveys, open‑source code analysis, algorithm implementation, cost savings, benchmark scores, and practical limitations across multiple scientific workflows.
Explore five standout open‑source projects—a React‑based 3D Tetris game, a multi‑dimensional code‑quality analyzer, an open alternative to Google NotebookLM, a terminal‑embedded AI assistant, and Meta's DINOv3 visual model family—each with repo links, key features, and practical use cases.
This article walks through installing JDGenie's Docker image, fixing configuration and Dockerfile issues, and evaluating its code‑analysis and animation‑generation capabilities against other open‑source agents, highlighting both its strengths and current limitations.
This article explains how to replace inefficient global searches for third‑party APIs with a TypeScript‑based solution that parses source files into an AST, traverses import declarations, distinguishes import styles, records call counts and line numbers, and overcomes symbol resolution challenges using the TypeScript compiler API.
This article investigates Vue 3.6’s new Vapor mode, comparing its compilation output with traditional Vue, revealing that while most bindings skip the virtual‑DOM and diff steps, the v‑for directive still relies on a full diff algorithm for complex list updates.
The EXPRESS 2025 workshop at ISSTA in Norway will showcase AI‑driven code auditing, present cutting‑edge research on trustworthy software systems, and invite researchers and practitioners to discuss transparency, reliability, and security challenges in modern software engineering.
This article explores how a multi‑agent AI system dramatically improves 0‑day vulnerability detection by automating code audit, reducing false positives, and outperforming traditional static analysis tools in large‑scale real‑world benchmarks.
The article introduces an AI‑driven automated testing system that streamlines code self‑testing, improves impact assessment, and generates comprehensive test reports, detailing its modular architecture, workflow, AI test engine, and future enhancements such as UI simulation and AI‑generated unit tests.
A veteran staff engineer spent years chasing a hidden GPU‑triggered shader bug until Claude Opus 4’s global code‑analysis and architecture‑diff capabilities pinpointed the flaw, slashing debugging effort from hundreds of hours to a few, while reshaping how developers collaborate with AI.
This article presents a comprehensive overview of the security challenges in HarmonyOS native ArkTS applications and describes the design and implementation of a specialized static analysis framework—including source extraction, data‑flow and inter‑function analysis, knowledge‑graph construction, and risk inference engine—while also outlining integration into development pipelines and future research directions.
The article analyzes how Claude combined with custom MCPs such as ClaudeCommander dramatically reduces the popularity of traditional IDEs by offering automatic codebase exploration, multi‑step task planning, and long‑running automation like video compression, while providing step‑by‑step installation and usage guidance.
This article explains how to analyse the impact range of code changes in large frontend projects, describes the architecture and core techniques—including project dependency‑tree building, AST parsing, GitLab diff extraction, and change propagation—provides concrete JavaScript/TypeScript examples, and discusses visualization of the results.
This article introduces JavaParser, an open‑source library for parsing Java source code into an AST, and walks through practical cases covering dependency setup, basic parsing, class and method extraction, code modification, class generation, and comprehensive analysis with code snippets and output screenshots.
This article examines how Kuaishou’s internal Mulan universal code analysis service tackled pipeline quality challenges by introducing on‑demand triggering, incremental checking, and unified rule infrastructure, resulting in dramatically faster static checks, lower rule‑development costs, comprehensive monitoring, and a rapid increase in rule coverage.
This article explains how to detect missing or unused Python packages, install the tach tool, configure it to analyze a project’s source root, and use its built‑in commands to list and verify external dependencies against the declared requirements, ensuring a clean and reproducible environment.
The latest GitStats release adds JSON report generation, extensive code refactoring with argparse replacing getopt, and full testing on Linux, Windows, and macOS, while outlining upcoming dark‑mode theming and a goal of 100% unit‑test coverage.
This article summarizes ByteDance’s quality‑efficiency expert Zhao Liang’s QCon presentation on using large language models to automatically generate unit tests, covering pain points, goals, data‑quality engineering, model‑analysis fusion, architecture, evaluation metrics, and future plans for a production‑grade testing tool.
The Precise Testing Platform combines a recommendation engine—featuring a link analyzer, diff analyzer, and knowledge base—to automatically construct detailed method‑call graphs from source code, extract HTTP and Dubbo APIs, handle reflections and inheritance, and store billions of nodes in Nebula Graph, thereby eliminating blind, missed, and redundant tests while boosting coverage and reducing testing costs.
This article provides a comprehensive walkthrough of Doris's SQL execution pipeline, covering the query optimizer's parsing, rewriting, and plan generation, the scheduler's fragment distribution, and the executor's fragment processing, including code examples of expression rewrite rules, join strategies, and data flow between FE and BE nodes.
This article details how a microservice‑based backend team designed and implemented a code‑analysis platform that creates a knowledge base, enables precise test selection and application slimming, and ultimately accelerates demand iteration while reducing dead code and unnecessary test runs.
This article introduces Python's Abstract Syntax Tree (AST), explains its purpose for code analysis and transformation, and provides ten detailed examples that demonstrate building, inspecting, modifying, and generating code using the ast module in a standard Python environment.
This tutorial teaches Java engineers how to build a JUnit4 Rule that captures test failures, extracts stack traces and source files, sends them to GPT for automated analysis, and logs the AI‑generated code improvement suggestions, complete with full example code and usage.
This article dissects the internal architecture of Kubernetes' kube-scheduler, walking through its initialization with Cobra, the Setup function, the creation of scheduler instances, the priority queue mechanics, scheduling cycles, and binding processes, providing comprehensive code examples to illuminate each step of the scheduling workflow.
This article describes how to construct a code‑analysis platform for Java micro‑services that builds a knowledge base through static, semi‑dynamic and dynamic analysis, enabling precise test‑case selection and safe removal of dead code to improve iteration efficiency and system maintainability.
A precise testing platform built on AST analysis and a recommendation engine was deployed across four core applications, enabling automated test execution with 100% pass rates, at least 75% service coverage, around 80% precision, early defect interception, and up to one hour per‑iteration time savings while planning further expansion and precision improvements.
This article explores the fundamentals of code understanding, including static, dynamic, and non‑code analysis, presents a three‑layer architecture for scalable code comprehension, and demonstrates practical AI‑enhanced applications such as intelligent unit testing, dead‑code detection, and AI‑based static analysis within CI/CD pipelines.
This article explains PHP's reflection capabilities, detailing how developers can inspect classes, interfaces, methods, and properties at runtime, and demonstrates practical uses such as dynamic object creation, method invocation, property manipulation, and annotation parsing with code examples.
Baidu’s white‑box code understanding platform combines static, dynamic, non‑code and LLM‑based analyses in a three‑layer architecture that accelerates C/C++ processing ninefold, supports multiple languages, and powers applications such as intelligent unit testing, orphan‑function cleanup and AI‑driven risk detection, while future integration with models like GPT‑4 aims to enable multi‑turn code Q&A, automated refactoring and predictive testing.
To accurately trim iOS app binaries, the article discards low‑precision Mach‑O/LinkMap methods and instead builds a custom compilation pipeline using libtooling and the Swift compiler to analyze full abstract syntax trees, enabling reliable detection of unused methods across complex language features and inheritance hierarchies.
This article explains how to convert TypeScript source code into an AST, traverse it to collect import statements, distinguish various import forms, and use the TypeScript compiler API to locate identifier symbols, enabling accurate counting of API calls and line numbers for a given dependency.
The article explains how Baidu App reduces its iOS package size by analyzing Link Map files and applying six code‑optimization techniques—unused class and module slimming, unused method pruning with LLVM, duplicate‑code detection, utility‑method consolidation, and A/B‑test hardening—yielding up to 8 MB of savings.
This article explains how rapid business growth leads to dead Java code, defines unused code at the method level, compares runtime and full‑method collection techniques, describes the algorithm for deriving not‑executed methods, and outlines an architecture that combines ServiceAbility Agent and java‑all‑call‑graph for systematic code slimming.
A seemingly harmless log addition caused a NullPointerException during FastJson serialization, prompting a step‑by‑step investigation of the generated ASM serializer, JavaBeanSerializer workflow, getter detection rules, and practical code‑style guidelines to avoid similar pitfalls.
This article presents a comprehensive approach to building an Android code impact analysis tool that leverages Git diff to locate modified lines, employs ASM-based class and method visitors to construct upward and downward call chains, extracts Javadoc and custom tags, and visualizes the results for developers and testers.
After taking over a system via a server image, the author uncovered malicious modifications that used a ternary expression to force id=1, causing MyBatis to generate a “where 1=1” clause that deleted the entire T_QUART_DATA table, and later discovered cron jobs that removed core jars, illustrating a thorough forensic debugging process.
This article explains how using fixed seeds with Java's Random class generates deterministic pseudo‑random strings that can be crafted to output "hello world", demonstrates the underlying seed mechanics, shows how to reverse‑engineer seeds for arbitrary phrases, and discusses related quirks in the Java source code.
This article walks through core Java concepts—including the compilation to bytecode, how reference types are passed, try‑catch‑finally return rules, servlet lifecycle stages, constructor fundamentals, and detailed analyses of several interview‑style code snippets—providing clear explanations and expected outputs.
The platform listens to GitLab change events, parses Java, ObjC, and Flutter diffs to locate modified methods, maps those methods to entry HTTP/RPC interfaces using recorded traffic call chains, and automatically selects corresponding regression test cases, dramatically cutting testing effort while enabling future risk analysis.
This article explains what an Abstract Syntax Tree (AST) is, demonstrates how to generate and inspect Python ASTs using the ast module, visualizes them with astpretty, and shows how to compile, evaluate, and transform AST nodes with custom visitors and transformers.
This article dissects Python’s standard pdb module, explaining its pure‑Python implementation on top of bdb and cmd, the event‑driven tracing mechanism, core debugging commands such as step, next, continue, and how MNN Workbench embeds these capabilities for mobile AI development.
This article examines why a dedicated StringJoiner helper class is useful, compares it with StringBuilder, explores rarely used features, and provides a detailed analysis of the JDK implementation—including member variables, constructors, add, toString, merge, length, and custom empty value handling—along with practical code examples.
This guide examines how deep learning techniques are applied to large‑scale code analysis, covering the technical workflow, program representations such as token sequences and AST paths, the code2vec architecture, its advantages, current limitations, and potential applications like code summarization and similarity detection.
This article explains why the original StringBuilder is limited, demonstrates how to use StringJoiner for comma‑separated strings, and provides a detailed analysis of the JDK source code including member fields, constructors, element addition, toString, length, merge, and empty‑value handling.
This article introduces Coco, an open‑source R&D efficiency tool that visualizes a project's layered architecture by counting code lines with CLOC and rendering interactive diagrams using D3.js, offering step‑by‑step installation, configuration, analysis, and real‑world examples.
This article explains how Alibaba Cloud’s intelligent syntax service leverages LSIF, Elasticsearch, and distributed scheduling to provide fast, cloud‑backed code navigation—eliminating the need for local clones and dramatically improving code review speed, accuracy, and resource efficiency.
This article presents a regression‑based approach that leverages historical bug‑fix data, feature selection, data cleaning, and model tuning to reorder redline scan warnings so developers can focus on the most critical fixes, improving overall repair efficiency.
Understanding JavaScript's Abstract Syntax Tree (AST) is crucial for modern code analysis, enabling tools like Babel, ESLint, and Webpack to parse, transform, and generate code beyond regex, with a clear process from lexical analysis to syntax analysis and standardized specifications such as ESTree.
IntelliJ IDEA 2019.2, released on July 24, 2019, brings JDK 13 support, smarter code suggestions, duplicate detection, structured search, folder‑specific settings, enhanced cursor movement, tab shortcuts, large‑file handling, performance boosts, refined debugging, tighter Git integration, and a revamped plugin center, all aimed at improving developer productivity.
This article analyzes Redis 6's newly introduced multithreaded I/O feature, explains its design and code implementation, presents benchmark configurations and results that show near‑doubling of GET/SET throughput, and discusses practical considerations and limitations of the approach.
The article reviews IntelliJ IDEA 2019.2, highlighting its JDK 13 support, smarter code hints, duplicate code detection, structured search, folder‑specific settings, cursor navigation tweaks, Tab shortcuts, large‑file handling, improved class creation dialogs, file size/time display, refined debugging windows, tighter Git integration, performance analysis tools, and overall UI enhancements, all illustrated with screenshots.
This article explains SonarQube's main components—including server processes, database, plugins, and scanners—and describes the end‑to‑end workflow that integrates code analysis into development, CI/CD pipelines, reporting, and operational monitoring.
The article explains what a Dex file is, how it is produced from Java .class files via the dx tool after JVM compilation, and why understanding Dex is crucial for Android tasks such as APK slimming, hot‑fixes, plugin architecture, app hardening, reverse engineering and overcoming the 64K method limit.
An analysis of over 1,900 open‑source PHP projects reveals the 100 functions most frequently used, highlighting common patterns, extensions, and best‑practice insights for developers.
This guide explains step‑by‑step how to deploy SonarQube on Azure using the Bitnami‑provided resource, retrieve the default admin credentials, configure VSTS (Azure DevOps) tasks, and set up continuous integration pipelines to automatically scan code quality during builds.
This guide explains how to download, install, and configure Alibaba's Java development guidelines plugin for IntelliJ IDEA and Eclipse, covering repository and manual installations, real‑time detection, Quick‑Fix features, scanning methods, result interpretation, and common troubleshooting steps.
This article reverse‑engineers a single‑line JavaScript snippet that creates a 128‑byte ray‑tracing demo, explains how the code works, refactors it for readability, and analyses the underlying arithmetic and bitwise operations that produce the patterned output.
