Quick Start

Prerequisites

• OpenSearch — storage and search for indexed data
• LLM provider — Ollama (local), DeepSeek, or Qwen for code enrichment

Both can be run locally via Docker.

Installation

# Via Cargo (recommended)
cargo install vibe-analyzer

# Or build from source
git clone https://gitcode.com/keygenqt_vz/vibe-analyzer.git
cd vibe-analyzer
cargo build --release

Starting Services

# OpenSearch
cd docker/opensearch && docker-compose up -d

# Open WebUI (optional, for AI assistant connection)
cd docker/open-webui && docker-compose up -d

Configuration

Config file: ~/.vibe-analyzer/config.json5 (created automatically on first run).

See Configuration for all options and detailed reference.

Usage

# Add a source
vibe-analyzer source add /path/to/project

# AST only (no LLM)
vibe-analyzer analyze export

# AST + LLM enrichment
vibe-analyzer analyze export -m meta,debt,errors

# Code files only, JSON5 format
vibe-analyzer analyze export -m debt -t code -f json5

# Index to OpenSearch
vibe-analyzer analyze index --target my-project

# Start MCP server for AI assistants
vibe-analyzer serve start

# View statistics
vibe-analyzer stats info

What’s Next

• Architecture — detailed breakdown
• CLI Reference — complete command reference
• Configuration — all config options
• Integrations — connecting AI assistants