grepai-quickstart

This skill provides a complete walkthrough to get GrepAI running and searching your code in 5 minutes. Verify: grepai version Verify: curl Navigate to your project and initialize GrepAI: This creates .grepai/config.yaml with default settings: Start the watch daemon to index your code: What happens: First indexing output: For long-running projects: Now search semantically: Trace function relationships: Be descriptive, not literal: Describe intent: Use English: After mastering the basics: Successful quickstart: - First time using GrepAI - Need a quick refresher on basic workflow - Setting up GrepAI on a new project - Demonstrating GrepAI to someone - Terminal access - A code project to index - Ollama as embedding provider - nomic-embed-text model - GOB file storage - Standard ignore patterns - Scans all source files (respects .gitignore ) - Chunks code into ~512 token segments - Generates embeddings via Ollama - Stores vectors in .grepai/index.gob - ✅ "user authentication and session management" - ❌ "auth" - ✅ "where errors are logged to the console" - ❌ "console.error" - Models are trained primarily on English text - Works best with English queries - Configure embeddings: See grepai-embeddings-* skills - Setup storage: See grepai-storage-* skills - Advanced search: See grepai-search-* skills - MCP integration: See grepai-mcp-* skills