
Grepai Init
- 589 installs
- 18 repo stars
- Updated February 1, 2026
- yoanbernabeu/grepai-skills
grepai-init is a Claude Code skill that bootstraps a local GrepAI semantic code index and configuration in an existing repository for developers setting up agent-powered code search workflows.
About
grepai-init is a setup skill from yoanbernabeu/grepai-skills that runs the grepai init command to create a .grepai directory in a project root. Initialization writes config.yaml for customization, prepares index.gob for the vector index populated by grepai watch, and symbols.gob for symbol metadata used in semantic search. Developers reach for grepai-init when onboarding GrepAI to a codebase for the first time or troubleshooting missing configuration before agent search sessions. The skill documents basic usage with cd into the project followed by grepai init, plus guidance on customizing initial settings and resolving initialization failures.
- Runs `grepai init` to create `.grepai/` with `config.yaml` and index placeholders
- Documents default embedder (Ollama `nomic-embed-text`) and gob vector store backend
- Explains chunking (512 size, 50 overlap) and watch debounce defaults
- Lists trace `enabled_languages` spanning Go, JS/TS, Python, Rust, and more
- Covers default ignore paths for `node_modules`, `vendor`, `.git`, and build artifacts
Grepai Init by the numbers
- 589 all-time installs (skills.sh)
- +5 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #1,603 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-initAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 589 |
|---|---|
| repo stars | ★ 18 |
| Security audit | 3 / 3 scanners passed |
| Last updated | February 1, 2026 |
| Repository | yoanbernabeu/grepai-skills ↗ |
How do you initialize GrepAI in an existing codebase?
Bootstrap a local GrepAI semantic code index and config in an existing repo before watch or agent search workflows.
Who is it for?
Developers adding GrepAI semantic code search to an existing repository before watch mode or agent query workflows.
Skip if: Repositories already initialized with .grepai or teams not using GrepAI for local semantic code indexing.
When should I use this skill?
The user sets up GrepAI for the first time, asks what grepai init creates, or troubleshoots missing .grepai configuration.
What you get
A .grepai directory with config.yaml, plus index.gob and symbols.gob paths ready for grepai watch indexing.
- .grepai/config.yaml
- .grepai/index.gob path
- .grepai/symbols.gob path
By the numbers
- Creates 3 core artifacts: config.yaml, index.gob, and symbols.gob under .grepai/
Files
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 initcreates - Customizing initial configuration
- Troubleshooting initialization issues
Basic Usage
cd /path/to/your/project
grepai initWhat 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:
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
- buildUnderstanding Default Settings
Embedder Settings
| Setting | Default | Purpose |
|---|---|---|
provider | ollama | Local embedding generation |
model | nomic-embed-text | 768-dimension model |
endpoint | http://localhost:11434 | Ollama API URL |
Store Settings
| Setting | Default | Purpose |
|---|---|---|
backend | gob | Local file storage |
Chunking Settings
| Setting | Default | Purpose |
|---|---|---|
size | 512 | Tokens per chunk |
overlap | 50 | Overlap for context |
Watch Settings
| Setting | Default | Purpose |
|---|---|---|
debounce_ms | 500 | Wait 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
embedder:
provider: openai
model: text-embedding-3-small
api_key: ${OPENAI_API_KEY}Change Storage Backend
store:
backend: postgres
postgres:
dsn: postgres://user:pass@localhost:5432/grepaiAdd Custom Ignore Patterns
ignore:
- .git
- .grepai
- node_modules
- "*.min.js"
- "*.bundle.js"
- coverage/
- .nyc_output/Init in Monorepos
For monorepos, init at the root:
cd /path/to/monorepo
grepai initOr use workspaces for separate indices:
grepai workspace create my-workspace
grepai workspace add my-workspace /path/to/project1
grepai workspace add my-workspace /path/to/project2Re-Initialization
If you need to reset:
# Remove existing config
rm -rf .grepai
# Re-initialize
grepai initWarning: This deletes your index. You'll need to re-run grepai watch.
Verifying Initialization
After init, verify with:
# Check config exists
cat .grepai/config.yaml
# Check status (will show no index yet)
grepai statusCommon Issues
❌ Problem: .grepai already exists ✅ Solution: Delete it first or edit existing config:
rm -rf .grepai && grepai init❌ Problem: Config created but Ollama not running ✅ Solution: Start Ollama before running grepai watch:
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
# 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 watchRelated skills
How it compares
Use grepai-init for first-time setup; use grepai watch skills after initialization to populate the vector index.
FAQ
What files does grepai init create?
grepai init creates a .grepai directory containing config.yaml for settings, index.gob for the vector index built by grepai watch, and symbols.gob for symbol metadata used in semantic code search.
When should developers run grepai-init?
Developers should run grepai-init when setting up GrepAI in a new codebase, customizing initial configuration, or troubleshooting missing .grepai files before starting watch or agent search workflows.
Is Grepai Init safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.