dev-agent

# dev-agent

[![Node.js](https://img.shields.io/badge/node-%3E%3D22-brightgreen.svg)](https://nodejs.org/)
[![pnpm](https://img.shields.io/badge/pnpm-8.15.4-orange.svg)](https://pnpm.io/)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

**Local semantic code search for Cursor and Claude Code via MCP.**

## What it does

dev-agent indexes your codebase and provides 9 MCP tools to AI assistants. Instead of AI tools grepping through files, they can ask conceptual questions like "where do we handle authentication?"

- `dev_search` — Semantic code search by meaning
- `dev_refs` — Find callers/callees of functions  
- `dev_map` — Codebase structure with change frequency
- `dev_history` — Semantic search over git commits
- `dev_plan` — Assemble context for GitHub issues
- `dev_inspect` — Inspect files (compare similar code, check patterns)
- `dev_gh` — Search GitHub issues/PRs semantically
- `dev_status` / `dev_health` — Monitoring

## Measured results

We benchmarked dev-agent against baseline Claude Code across 5 task types:

| Metric | Baseline | With dev-agent | Change |
|--------|----------|----------------|--------|
| Cost | $1.82 | $1.02 | **-44%** |
| Time | 14.1 min | 11.5 min | **-19%** |
| Tool calls | 69 | 40 | **-42%** |

**Trade-offs:** Faster but sometimes less thorough. Best for implementation tasks and codebase exploration. For deep debugging, baseline Cursor may read more files.

## When to use it

**Good fit:**
- Large or unfamiliar codebases
- Implementation tasks ("add a feature like X")
- Exploring how code works
- Reducing AI API costs

**Less useful:**
- Small codebases you already know well
- Deep debugging sessions
- When thoroughness matters more than speed

## Quick Start

```bash
# Install globally
npm install -g dev-agent

# Index your repository (initial indexing can take 5-10 minutes for large codebases)
cd /path/to/your/repo
dev index .

# Install MCP integration
dev mcp install --cursor  # For Cursor IDE
dev m