v0.3.1 is now available
██╗   ██╗██╗██████╗ ███████╗██████╗  █████╗  ██████╗ 
██║   ██║██║██╔══██╗██╔════╝██╔══██╗██╔══██╗██╔════╝ 
██║   ██║██║██████╔╝█████╗  ██████╔╝███████║██║  ███╗
╚██╗ ██╔╝██║██╔══██╗██╔══╝  ██╔══██╗██╔══██║██║   ██║
 ╚████╔╝ ██║██████╔╝███████╗██║  ██║██║  ██║╚██████╔╝
    ╚═══╝  ╚═╝╚═════╝ ╚══════╝╚═╝  ╚═╝╚═╝  ╚═╝ ╚═════╝   

VibeRAG is a free, open-source MCP server for semantic and hybrid search for your codebase. Faster, Exhaustive, Exploratory Search for Coding Agents.

$ npm install -g viberag
COPY
Powering Your Favorite Agents
Claude Code Cursor Gemini CLI JetBrains IDEs OpenAI Codex OpenCode Roo Code VS Code Copilot Windsurf Zed and others...
Unlock Deep Context

Supercharge Your Prompts

Stop pasting file contents. Stop hoping your agent guesses the right filename. Invoke the magic words use viberag and your coding agent will use semantic search find everything.

Intent-Based Retrieval

You don't need to know the filename. Ask "how is billing handled?" and Viberag finds StripeService.ts and Invoice.go automatically.

Token Efficiency

Instead of dumping entire directories into context, Viberag retrieves only the 20-30 relevant code chunks, saving tokens and improving accuracy.

Exhaustive Search

Prevent missing context. Whether planning a feature or refactoring, Viberag ensures your agent sees every relevant reference, catching edge cases that simple keyword searches miss.

Why Keywords Aren't Enough

In large polyglot monorepos, concepts are scattered. Standard agents "guess" file and function names using grep-like logic. Viberag understands meaning.

Standard Agent

Query:
"How do we validate user permissions?"
Guesses filenames: "permission.ts", "validate.js"
Greps for "validateUser"
Misses: auth_middleware.go (Golang backend)
Misses: Guard.py (Python service)
Incomplete Context
Agent hallucinates or asks you to open files manually.

With Viberag

Query:
"Use viberag to find how permissions are validated."
Vector Search matches concept "Validation""Guard"
Cross-language retrieval (TS, Go, Python)
src/middleware/AuthGuard.ts 92% match
pkg/auth/rbac.go 89% match
Full Semantic Context
Agent sees the actual logic, regardless of keywords.
Zero Config Needed

Automated Setup & Indexing

VibeRAG handles the heavy lifting. Run the initialization wizard to configure your preferred embedding model (local or cloud) and let the file watcher keep your index in sync.

$ viberag
Launch CLI

/init Wizard

Interactive CLI command to set up embeddings, download models, and index your codebase for the first time.

/mcp-setup

Automatically configures Claude Code, Cursor, and VS Code config files to connect to the VibeRAG MCP server.

Agent-Aware Watch Mode

Your agent automatically starts VibeRAG's watch mode. It detects code changes and instantly updates the search index, so your agent always has the latest context without manual re-indexing.

viberag — -zsh — 80x24

How it Works

Seamless integration from disk to context.

1

Parse & Embed

Tree-sitter parses your code into semantic chunks. Embeddings are generated locally or via API and stored in LanceDB.

2

Auto-Launch & Watch

The Editor / agent automatically starts viberag which starts watching for file changes. The Agent has access to its search tools and can monitor the indexing status.

3

Hybrid Search

Your agent queries the server. VibeRAG performs a hybrid search (Dense Vector + BM25 Keyword) to return the most relevant code snippets.

Exposed MCP Tools

VibeRAG exposes these powerful tools to your connected AI agents.

codebase_search

Semantic, keyword, or hybrid search.

codebase_parallel_search

Run multiple search strategies simultaneously.

viberag_index

Manually trigger indexing (usually automatic).

viberag_status

Get index health and stats.

viberag_watch_status

Check file watcher status.

Precision Parsing

Syntax-Aware Chunking

VibeRAG uses Tree-sitter to parse code into an Abstract Syntax Tree (AST). It creates semantic boundaries—keeping functions, classes, and scopes intact—so the embedding model captures the complete logical unit.

Native Parsers Active
JavaScript
.js, .mjs, .cjs
TypeScript
.ts, .mts, .cts
TSX
.tsx
Python
.py
Go
.go
Rust
.rs
Java
.java
C#
.cs
Swift
.swift
Kotlin
.kt, .kts
PHP
.php
Dart
.dart

Flexible Embedding Models

Choose between complete privacy or state-of-the-art cloud performance. VibeRAG adapts to your security requirements.

Offline

Locally Generated Embeddings

Powered by Qwen 3 0.6B. High quality local / offline embedding generation.

  • Local, Free, No API Keys
  • Code & Natural Language understanding
  • Zero data egress
Frontier

API Embedding Providers

Connect to OpenAI, Gemini, or Mistral for state-of-the-art semantic understanding.

  • Fastest generation speed
  • Highest Semantic Understanding
  • Still very cheap