Skip to content

introduction.mdx

Latest commit

 

History

History
62 lines (51 loc) · 2.34 KB

introduction.mdx

File metadata and controls

62 lines (51 loc) · 2.34 KB
title Introduction
description Semantic code search + knowledge graph as an MCP plugin for Claude Code

What is VecGrep?

VecGrep is a semantic code search and knowledge graph tool that works as an MCP (Model Context Protocol) plugin for Claude Code.

Instead of grepping 50 files and sending 30,000 tokens to Claude, VecGrep returns only what's relevant:

Mode Avg tokens vs raw files Latency
Raw file read 26,009 — —
search_code ~3,007 −88% ~83ms
hybrid_search ~3,324 −87% ~76ms
search_graph ~47 −99.8% ~3ms

How it works

Parses source files with tree-sitter to extract semantic units — functions, classes, and methods. Encodes each chunk locally using [`all-MiniLM-L6-v2-code-search-512`](https://huggingface.co/isuruwijesiri/all-MiniLM-L6-v2-code-search-512) (384-dim, ~80MB one-time download) via the fastembed ONNX backend (~100ms startup) or PyTorch. Saves embeddings and metadata in LanceDB, and optionally a knowledge graph (`graph.json`), under `~/.vecgrep//`. Uses an ANN index (IVF-PQ) for fast approximate search, keyword search over graph nodes, or a blended hybrid of both.

Incremental re-indexing via mtime/size checks skips unchanged files.

Which tool to use

Query type Tool
Semantic / behaviour ("how does authentication work") search_code
Structural / navigation ("where is class X defined", "what calls Y") search_graph
Both semantic and structural context needed hybrid_search
Explore call graph or inheritance graph_neighbors

Key features

Returns only relevant chunks or graph nodes instead of entire files. ONNX backend starts in ~100ms. No PyTorch required by default. AST-based graph index captures calls, imports, inheritance — no LLM required. Claude decides when to call VecGrep — no manual invocation needed.