source-code-analysis

Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

Emerge is a browser-based interactive codebase and dependency visualization tool for many different programming languages. It supports some basic code quality and graph metrics and provides a simple and intuitive way to explore and analyze a codebase by using graph structures.

Concurrently detect the minimum Python versions needed to run code

Chapter-by-chapter teardown of a production coding agent — agent loop, context engineering, compaction, permissions, MCP. 13 chapters, Chinese and English.

CodeWiki is a knowledge platform that analyzes repositories into AST graphs, builds GraphRAG indexes, and generates source-grounded developer wikis with FastAPI, React, and LiteLLM.

Python tool that clones two Git repositories and reports lines of code appearing in both, with per-file duplication statistics

Source code graph RAG (GraphRAG) for C/C++ development based on clang/clangd

A toolkit for pre-processing large source code corpora

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

CFG based program similarity using Graph Neural Networks

an implementation of "code2vec: Learning Distributed Representations of Code"

Clade is a tool for extracting information about software build process and source code

detect programming language of source in pure python from an ensemble of classifiers

Agent Skill: Architecture-level cross-stack source code asset scanner. Know what you have before you refactor. | 架构级跨技术栈源码资产扫描工具

Source code graph RAG (graphRAG) for Java/Kotlin development based on jQAssistant

Improving Source Code Similarity Detection with GraphCodeBERT and Additional Feature Integration

NEXUS REDFOX — Local-first code intelligence and security analysis platform for developers and security researchers.

Unified solution for SemEval-2026 Task 13: GenAI Code Detection & Attribution. A modular framework covering Subtasks A (Detection), B (Authorship), and C (Mixed-Source Analysis), designed to distinguish and analyze LLM-generated vs. Human code with a centralized pipeline.

Offline-first, multi-language SAST with semantic data-flow analysis, deterministic security rules, SARIF/PDF reporting, Docker isolation, and optional local Ollama enrichment.

TONBI is a source code auditing scanner against framework based web application. It hunts for various vulnerabilites in such as Laravel, Codeigniter, Django, Flask, Rails , etc ... It's simple, easy, and intuitive! It gives the most efficient code auditing method especially for security researchers and also all the web application developers.