# VecGrep

> Use this tool when you need to perform efficient semantic code searches across large codebases, solving problems like finding relevant code snippets or identifying similar functions and classes. VecGrep takes in source files and returns top semantically relevant code chunks, reducing token output and improving query results. It is ideal for use cases involving multi-language codebases, supporting local and cloud-based deployments with flexible configuration options.

Canonical page: https://skillsregistry.net/skills/iamvirul-vecgrep  
JSON: https://api.skillsregistry.net/v1/skills/iamvirul-vecgrep

## Description

Provides semantic code search by parsing source files with tree-sitter into functions, classes, and methods, then encoding them with vector embeddings stored in LanceDB. Supports local ONNX embeddings with ~100ms startup as well as cloud providers (OpenAI, Voyage AI, Google Gemini) via bring-your-own-key configuration. Returns the top semantically relevant code chunks instead of entire files, achieving significant token reduction for codebase queries. Supports incremental re-indexing, 10+ programming languages, and approximate nearest neighbor search via IVF-PQ indexing.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/iamvirul-vecgrep)
- **Repository:** <https://github.com/vecgrep/vecgrep>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "iamvirul-vecgrep"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/iamvirul-vecgrep` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/iamvirul-vecgrep/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt