每个 AI agent 都会读文件,但很少有 agent 知道哪些文件总是一起被修改、哪个决定是哪一天做的。repowise 把依赖图、Git 历史和架构决策编成一张可查询的地图,通过 MCP 递到 agent 手里。它回答的不是「这个文件写了什么」,而是「这段代码为什么长这样」。
-
Updated
Aug 1, 2026 - Python
每个 AI agent 都会读文件,但很少有 agent 知道哪些文件总是一起被修改、哪个决定是哪一天做的。repowise 把依赖图、Git 历史和架构决策编成一张可查询的地图,通过 MCP 递到 agent 手里。它回答的不是「这个文件写了什么」,而是「这段代码为什么长这样」。
Analyze Git repository and generate historical archaeology reports with SQLite, CSV/JSON exports, charts, and HTML/Markdown slides.
🧭 Instant codebase tour generator. One command → interactive HTML guide in 60s: architecture, module experts, API & DB maps, newcomer checklist. 100% local, zero deps.
🔍 Git Repository Analytics Tool 📈 Analyze commit frequency and development activity 🚫 Flag poor commit messages and hygiene issues 🕳️ Detect dead (inactive) days in the commit timeline 🧠 Reveal the real development patterns of a Git repository Built with ⚙️ Git internals, 🐍 Python, and 📊 data analysis
codet is a command-line tool for analyzing the code commit trail to understand how this feature work, leverage tools like cursor/windsurf/trae/LLMs-tool to provide a foundation for project or feature fast warm-up
Small scripts I use to analyze large / old codebases
悟空GitHub采集器(GitHub 抓取工具 - GitHub 爬虫工具),支持GitHub用户数据采集与开发者画像分析,支持在线使用或者EXE。Goku GitHub Scraper is a tool for collecting and analyzing GitHub user data, providing developer profiling and insights. It supports both online usage and desktop (EXE) deployment.
Measure AI co-programming effectiveness on any git repo. Detects Claude/Copilot/Cursor/Codex signatures and triangulates productivity multipliers via top-down roles, bottom-up formula, and an optional Claude Code subagent that reads diffs.
Evidence-backed job fit assessments from your resume and local git repos. Chrome extension for real-time job board grading, interactive dashboard, cover letter generation, and proof packages. Privacy-first — all processing stays local.
AI-powered Software Health Intelligence Platform for predictive technical debt analysis, architecture smell detection, and repository analytics.
A CLI tool that scans your codebase and roasts it. 🔥 Analyze your repo, find issues, and get brutally honest feedback—because your code deserves it.
Deterministic Git contribution analysis for workload, difficulty, and resume-ready summaries.
Github Repo Analyzer
Test impact analysis and code intelligence for LLM agents. Zero dependencies. 15 MCP tools.
AI-powered Git patch reporter. PatchMind scans your Git repo and generates clean, standalone HTML reports showing patch-level diffs, file history, tree changes, risk scoring, and blame data. Built for devs who want smarter insight into their codebase — no cloud, no clutter, just local clarity.
A local AI pair-programmer that learns your coding style and retains memory across sessions.
🧬 Atrophy — your coding skills have a half-life. Analyze your git history to see what you wrote, what AI wrote, and which skills are fading.
Measure refactoring, duplication and churn from your own git history. Compare any two periods — for example, before and after your team adopted AI coding tools. Runs entirely locally; no code leaves your machine.
To associate your repository with the git-analysis topic, visit your repo's landing page and select "manage topics."