> ## Documentation Index
> Fetch the complete documentation index at: https://vecgrep.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Start searching your codebase in under a minute

## Usage with Claude

You don't trigger VecGrep manually — Claude decides when to call the tools based on what you ask.

| What you say to Claude                                 | Tool invoked       |
| ------------------------------------------------------ | ------------------ |
| "Index my project at /Users/me/myapp"                  | `index_codebase`   |
| "How does authentication work in this codebase?"       | `search_code`      |
| "Find where database connections are set up"           | `search_code`      |
| "Build a knowledge graph of my project"                | `index_graph`      |
| "Where is the UserService class defined?"              | `search_graph`     |
| "What does authenticate\_user call?"                   | `graph_neighbors`  |
| "Find auth code, including structurally related files" | `hybrid_search`    |
| "How many files are indexed?"                          | `get_index_status` |

## Typical first-time flow

```
You:    "Search for how payments are handled in /Users/me/myapp"
Claude: [calls index_codebase automatically since no index exists]
Claude: [calls search_code with your query]
Claude: "Here's how payments work — in src/payments.py:42..."
```

After the first index, subsequent searches skip unchanged files automatically — no re-indexing needed unless your code changes.

## Using the knowledge graph

```
You:    "Build the graph index for /Users/me/myapp, then show me what PaymentService calls"
Claude: [calls index_graph]
Claude: [calls search_graph to locate PaymentService]
Claude: [calls graph_neighbors to show its callees]
Claude: "PaymentService.charge calls: stripe_client.create_charge, audit.log_payment, ..."
```

> The graph index is optional. All existing `search_code` workflows continue to work unchanged.