Grepai Init

yoanbernabeu/grepai-skills/skills/configuration/grepai-init

by yoanbernabeu382d40261c0d41109c6e11872574ba0be9b064d0No licenseListed Oct 9, 2026Updated Oct 9, 2026

Initialize GrepAI in a project. Use this skill when setting up GrepAI for the first time in a codebase.

Instructions onlySoftware Development
AI-generated overview

Explains how to initialize GrepAI in a project, covering the grepai init command, generated config, and troubleshooting.

What it does
This skill documents the grepai init command and what project initialization creates. It describes the generated .grepai directory, the default config.yaml settings for embedder, store, chunking, watch, trace, and ignore patterns, and how to customize them. It also covers monorepo and workspace setups, re-initialization, verification steps, common issues, and best practices.
When to use it
Use it when setting up GrepAI for the first time in a codebase, when you need to understand or customize the initial configuration, or when troubleshooting initialization problems.
Requirements
Requires the GrepAI CLI to be installed and run in a project directory. The default configuration expects a local Ollama server at with the nomic-embed-text model. No scripts ship with this skill; it is instructions only.

GrepAI Init

This skill covers the grepai init command and project initialization.

When to Use This Skill

  • Setting up GrepAI in a new project
  • Understanding what grepai init creates
  • Customizing initial configuration
  • Troubleshooting initialization issues

Basic Usage

bash
cd /path/to/your/projectgrepai init

What Init Creates

Running grepai init creates the .grepai/ directory with:

.grepai/├── config.yaml    # Configuration file├── index.gob      # Vector index (created by watch)└── symbols.gob    # Symbol index for trace (created by watch)

Default Configuration

The generated config.yaml:

yaml
version: 1
embedder:  provider: ollama  model: nomic-embed-text  endpoint: http://localhost:11434
store:  backend: gob
chunking:  size: 512  overlap: 50
watch:  debounce_ms: 500
trace:  mode: fast  enabled_languages:    - .go    - .js    - .ts    - .jsx    - .tsx    - .py    - .php    - .c    - .h    - .cpp    - .hpp    - .cc    - .cxx    - .rs    - .zig    - .cs    - .pas    - .dpr
ignore:  - .git  - .grepai  - node_modules  - vendor  - target  - __pycache__  - dist  - build

Understanding Default Settings

Embedder Settings

SettingDefaultPurpose
providerollamaLocal embedding generation
modelnomic-embed-text768-dimension model
endpointhttp://localhost:11434Ollama API URL

Store Settings

SettingDefaultPurpose
backendgobLocal file storage

Chunking Settings

SettingDefaultPurpose
size512Tokens per chunk
overlap50Overlap for context

Watch Settings

SettingDefaultPurpose
debounce_ms500Wait time before re-indexing

Ignore Patterns

Default patterns exclude:

  • Version control: .git
  • GrepAI data: .grepai
  • Dependencies: node_modules, vendor
  • Build outputs: target, dist, build
  • Cache: __pycache__

Customizing After Init

Edit .grepai/config.yaml to customize:

Change Embedding Provider

yaml
embedder:  provider: openai  model: text-embedding-3-small  api_key: ${OPENAI_API_KEY}

Change Storage Backend

yaml
store:  backend: postgres  postgres:    dsn: postgres://user:pass@localhost:5432/grepai

Add Custom Ignore Patterns

yaml
ignore:  - .git  - .grepai  - node_modules  - "*.min.js"  - "*.bundle.js"  - coverage/  - .nyc_output/

Init in Monorepos

For monorepos, init at the root:

bash
cd /path/to/monorepogrepai init

Or use workspaces for separate indices:

bash
grepai workspace create my-workspacegrepai workspace add my-workspace /path/to/project1grepai workspace add my-workspace /path/to/project2

Re-Initialization

If you need to reset:

bash
# Remove existing configrm -rf .grepai
# Re-initializegrepai init

Warning: This deletes your index. You'll need to re-run grepai watch.

Verifying Initialization

After init, verify with:

bash
# Check config existscat .grepai/config.yaml
# Check status (will show no index yet)grepai status

Common Issues

❌ Problem: .grepai already exists ✅ Solution: Delete it first or edit existing config:

bash
rm -rf .grepai && grepai init

❌ Problem: Config created but Ollama not running ✅ Solution: Start Ollama before running grepai watch:

bash
ollama serve

❌ Problem: Wrong directory initialized ✅ Solution: Remove .grepai and init in correct directory

Best Practices

  1. Init at project root: Where your main code lives
  2. Add .grepai/ to .gitignore: Index is machine-specific
  3. Customize ignore patterns: Exclude generated/vendored code
  4. Review config after init: Adjust for your stack

Example .gitignore Addition

gitignore
# GrepAI.grepai/

Output Format

After successful initialization:

✅ GrepAI Initialized
   Config: .grepai/config.yaml
   Default settings:   - Embedder: Ollama (nomic-embed-text)   - Storage: GOB (local file)   - Chunking: 512 tokens, 50 overlap
   Next steps:   1. Ensure Ollama is running: ollama serve   2. Start indexing: grepai watch

Source and attribution

Source:yoanbernabeu/grepai-skillsinskills/configuration/grepai-initat commit382d402

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal