██╗ ██╗██╗██████╗ ███████╗██████╗ █████╗ ██████╗
██║ ██║██║██╔══██╗██╔════╝██╔══██╗██╔══██╗██╔════╝
██║ ██║██║██████╔╝█████╗ ██████╔╝███████║██║ ███╗
╚██╗ ██╔╝██║██╔══██╗██╔══╝ ██╔══██╗██╔══██║██║ ██║
╚████╔╝ ██║██████╔╝███████╗██║ ██║██║ ██║╚██████╔╝
╚═══╝ ╚═╝╚═════╝ ╚══════╝╚═╝ ╚═╝╚═╝ ╚═╝ ╚═════╝ VibeRAG is a free, open-source MCP server for semantic and hybrid search for your codebase. Faster, Exhaustive, Exploratory Search for Coding Agents.
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.
You don't need to know the filename. Ask "how is billing handled?" and Viberag finds StripeService.ts and Invoice.go automatically.
Instead of dumping entire directories into context, Viberag retrieves only the 20-30 relevant code chunks, saving tokens and improving accuracy.
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.
In large polyglot monorepos, concepts are scattered. Standard agents "guess" file and function names using grep-like logic. Viberag understands meaning.
auth_middleware.go (Golang backend) Guard.py (Python service) src/middleware/AuthGuard.ts 92% match pkg/auth/rbac.go 89% match 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.
Interactive CLI command to set up embeddings, download models, and index your codebase for the first time.
Automatically configures Claude Code, Cursor, and VS Code config files to connect to the VibeRAG MCP server.
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.
Seamless integration from disk to context.
Tree-sitter parses your code into semantic chunks. Embeddings are generated locally or via API and stored in LanceDB.
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.
Your agent queries the server. VibeRAG performs a hybrid search (Dense Vector + BM25 Keyword) to return the most relevant code snippets.
VibeRAG exposes these powerful tools to your connected AI agents.
Semantic, keyword, or hybrid search.
Run multiple search strategies simultaneously.
Manually trigger indexing (usually automatic).
Get index health and stats.
Check file watcher status.
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.
Choose between complete privacy or state-of-the-art cloud performance. VibeRAG adapts to your security requirements.
Powered by Qwen 3 0.6B. High quality local / offline embedding generation.
Connect to OpenAI, Gemini, or Mistral for state-of-the-art semantic understanding.