Introduction

dev-agent provides semantic code search to AI assistants like Cursor and Claude Code via MCP.

We built this for ourselves. When exploring large codebases, we found AI tools spending too much time grepping through files and reading entire files to find relevant code. dev-agent gives them a faster path: search by meaning and get code snippets.

What it does

Indexes your codebase locally with embeddings (BAAI/bge-small-en-v1.5)
Returns code snippets — not just file paths, reducing input tokens by 99%
Provides semantic search — find code by meaning, not just keywords

Measured impact

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

Task Type	Cost Savings	Time Savings	Why
Debugging	42%	37%	Semantic search beats grep chains
Exploration	44%	19%	Find code by meaning
Implementation	29%	22%	Semantic search finds relevant code

Key insight: Savings scale with task complexity. Simple lookups show no improvement; complex debugging shows 42% cost reduction.

Trade-off: Faster but sometimes less thorough. Baseline Claude provides more diagnostic shell commands.

Why it saves money

What dev-agent does	Manual equivalent	Impact
Returns code snippets in search	Read entire files	99% fewer input tokens
Semantic search finds relevant code	grep chains + filtering	42% cost reduction

Key Features

Feature	Description
Code Snippets	Search returns code, not just file paths
Semantic Search	Find code by meaning, not keywords
100% Local	Your code never leaves your machine

Architecture

dev-agent is a monorepo:

@prosdevlab/dev-agent-core — Scanning, vector storage, GitHub integration
@prosdevlab/dev-agent-cli — Command-line interface
@prosdevlab/dev-agent-mcp — MCP server with 6 tool adapters
@prosdevlab/dev-agent-subagents — Planner, explorer agents

Next Steps

Installation → — Get dev-agent installed in under 2 minutes
Quickstart → — Index and search in 5 minutes