GitIntelAI

# GitIntel

[![CI](https://github.com/gitintel-ai/GitIntelAI/actions/workflows/ci.yml/badge.svg)](https://github.com/gitintel-ai/GitIntelAI/actions)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
[![Version](https://img.shields.io/badge/version-0.1.0--beta-blue)](packages/cli/Cargo.toml)
[![Rust](https://img.shields.io/badge/built%20with-Rust-orange)](https://www.rust-lang.org)
[![GitHub stars](https://img.shields.io/github/stars/gitintel-ai/GitIntelAI?style=social)](https://github.com/gitintel-ai/GitIntelAI)

> Do you know how much of your codebase is AI-generated?

GitIntel tracks AI authorship in your git history -- line by line, commit by commit.
**The missing `git blame` for AI code.**

<p align="center">
  <img src="demo/hero.svg" alt="GitIntel Demo — scan, blame, stats" width="800">
</p>

## The Problem

Engineering teams use Claude Code, Cursor, and Cursor daily. But nobody can answer:

- What percentage of our code is AI-written?
- What does AI coding actually cost per sprint?
- Which developers and agents produce the most code?

GitIntel answers all three. Zero workflow change. 100% local.

## Install

```bash
# macOS / Linux
curl -fsSL https://gitintel.com/install | sh

# Homebrew
brew install gitintel-ai/tap/gitintel

# Windows (PowerShell)
irm https://gitintel.com/install.ps1 | iex

# npm (any platform)
npx @gitintel-cli/gitintel
```

<details>
<summary>Build from source</summary>

```bash
git clone https://github.com/gitintel-ai/GitIntelAI.git && cd GitIntelAI
cargo build --release --manifest-path packages/cli/Cargo.toml
cp packages/cli/target/release/gitintel ~/.local/bin/
```

Requires Rust 1.82+ ([rustup.rs](https://rustup.rs)) and Git 2.30+.
</details>

## Quick Start

```bash
cd your-project/
gitintel init          # install hooks, create local DB
gitintel checkpoint \
  --file "src/api.ts" \
  --lines "12-45,78-103"   # --agent and --model are optional
git commit -m "Add auth flow"   # hook fires, attribution rec