Skip to Content
Home

dev-agent

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

Get Started · View on GitHub 

v0.5.0 coming soon — Arrow functions, React hooks, and exported constants now indexed. See what’s new →

Built by engineers, for engineers. An MCP server that gives your AI tools semantic code search and context bundling. Savings scale with task complexity — up to 42% on debugging tasks.

Why it saves money

dev-agent doesn’t just search — it bundles context so Claude reads less:

What dev-agent doesManual equivalentSavings
Returns code snippets in searchRead entire files99% fewer input tokens
dev_plan bundles issue + code + commits5-10 separate tool calls29% cost reduction
Semantic search finds relevant codegrep chains + manual filtering42% cost reduction

The harder the task, the bigger the savings.

Measured results by task type

Task TypeCost SavingsTime SavingsWhy
Debugging42%37%Semantic search beats grep for “where is the bug?”
Exploration44%19%Find code by meaning, not keywords
Implementation29%22%dev_plan bundles context in one call
Simple lookup~0%~0%Both approaches are fast

Trade-off: Faster but sometimes less thorough. Baseline Claude provides more diagnostic shell commands. dev-agent excels when you need to explore or understand code.

Same question, different approach

We asked Claude Code: “Debug why search returns duplicates”

Claude’s approach:

  • Read indexer/index.ts (441 lines)
  • Read vector/store.ts (258 lines)
  • Read scanner/typescript.ts (full file)
  • Read scanner/markdown.ts (full file)

Result: 18+ tool calls, 10 files read → $1.37, 12 minutes

18,800 input tokens consumed

Same root cause identified. 42% cheaper. 37% faster.

Context bundling: dev_plan

For implementation tasks, dev_plan bundles everything in one call:

Claude’s approach for “Implement issue #61”:

gh issue view 61 --json title,body # Fetch issue grep "--json" -r packages/cli # Find existing flags Read search.ts # Check implementation Read mcp.ts # Check implementation Read config.ts # Check file writes # ... 5+ more tool calls

Result: $0.55, 5.7 minutes

How it works

Key insight: dev-agent returns code snippets with context — Claude doesn’t read entire files. This is why input tokens drop by 99%.

Quick Start

Install

npm install -g dev-agent

Index your repository

cd your-project dev index .

Connect to your AI tool

dev mcp install --cursor # For Cursor dev mcp install # For Claude Code

9 MCP Tools

ToolWhat it does
dev_searchSemantic code search — returns snippets, not just paths
dev_planContext bundling — issue + code + commits in one call
dev_refsFind callers/callees of any function
dev_mapCodebase structure with change frequency
dev_historySemantic search over git commits
dev_exploreFind similar code, trace relationships
dev_ghSearch GitHub issues/PRs semantically
dev_statusRepository indexing status
dev_healthServer health checks

When to use it

Scenariodev-agent?Expected Savings
Debugging unfamiliar codeâś… Yes42% cost
Exploring large codebaseâś… Yes44% cost
Implementing GitHub issuesâś… Yes29% cost
Small codebase you know❌ Skip~0%
Need exhaustive file reads⚠️ MaybeTrade speed for thoroughness

Features

  • Context Bundling — dev_plan replaces 5-10 tool calls with one
  • Code Snippets — Search returns code, not just file paths
  • 100% Local — Your code never leaves your machine
  • Sub-second Search — Fast even on large repos with LanceDB
  • 1379+ Tests — Production-grade reliability

Read the story behind dev-agent → 

MIT License • Built by prosdev 

Last updated on