
Grepai Quickstart
- 550 installs
- 18 repo stars
- Updated February 1, 2026
- yoanbernabeu/grepai-skills
grepai-quickstart is a CLI onboarding skill that walks developers through installing GrepAI, indexing a repository, and running first semantic code searches for coding agents in about five minutes.
About
grepai-quickstart is a yoanbernabeu/grepai-skills walkthrough that gets GrepAI running on a local codebase in about five minutes. Prerequisites are terminal access and a code project to index. Step 1 installs GrepAI via Homebrew (brew install yoanbernabeu/tap/grepai) or a curl-based Linux/macOS script from the upstream repository. The skill targets first-time setup, quick refreshes, new-project indexing, and demos of semantic repository search to teammates. After install, agents gain locally indexed semantic search over the repo instead of relying on brittle text grep alone. Developers reach for grepai-quickstart when onboarding GrepAI before deeper grepai-skills workflows or when standing up agent context on a fresh checkout.
- Complete 5-minute path: install GrepAI, Ollama, init, index, search
- Install paths for macOS Homebrew, curl install.sh, and Windows PowerShell
- Local embeddings via Ollama with nomic-embed-text and default .grepai/config.yaml
- Covers first-time setup, new project setup, and demo walkthroughs
- Verify steps for grepai version and Ollama API tags
Grepai Quickstart by the numbers
- 550 all-time installs (skills.sh)
- +4 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #1,674 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: CRITICAL risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/yoanbernabeu/grepai-skills --skill grepai-quickstartAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 550 |
|---|---|
| repo stars | ★ 18 |
| Security audit | 1 / 3 scanners passed |
| Last updated | February 1, 2026 |
| Repository | yoanbernabeu/grepai-skills ↗ |
How do you set up GrepAI semantic repo search?
Stand up GrepAI on a codebase in minutes so your coding agent can semantic-search the repo locally.
Who is it for?
Developers onboarding GrepAI for the first time or re-indexing a new repository before agent-assisted semantic search.
Skip if: Teams already running GrepAI who need advanced query tuning instead of install-and-first-search basics.
When should I use this skill?
User is new to GrepAI, needs a refresher, or wants GrepAI installed and indexed on a new project quickly.
What you get
Installed GrepAI CLI, indexed project corpus, and working semantic search queries over local source files.
- Installed GrepAI CLI
- Indexed repository
- First semantic search results
By the numbers
- Marketed as a 5-minute install-to-first-search walkthrough
Files
GrepAI Quickstart
This skill provides a complete walkthrough to get GrepAI running and searching your code in 5 minutes.
When to Use This Skill
- First time using GrepAI
- Need a quick refresher on basic workflow
- Setting up GrepAI on a new project
- Demonstrating GrepAI to someone
Prerequisites
- Terminal access
- A code project to index
Step 1: Install GrepAI
macOS
brew install yoanbernabeu/tap/grepaiLinux/macOS (Alternative)
curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | shWindows
irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iexVerify: grepai version
Step 2: Install Ollama (Local Embeddings)
macOS
brew install ollama
ollama serve &
ollama pull nomic-embed-textLinux
curl -fsSL https://ollama.com/install.sh | sh
ollama serve &
ollama pull nomic-embed-textVerify: curl http://localhost:11434/api/tags
Step 3: Initialize Your Project
Navigate to your project and initialize GrepAI:
cd /path/to/your/project
grepai initThis creates .grepai/config.yaml with default settings:
- Ollama as embedding provider
nomic-embed-textmodel- GOB file storage
- Standard ignore patterns
Step 4: Start Indexing
Start the watch daemon to index your code:
grepai watchWhat happens: 1. Scans all source files (respects .gitignore) 2. Chunks code into ~512 token segments 3. Generates embeddings via Ollama 4. Stores vectors in .grepai/index.gob
First indexing output:
🔍 GrepAI Watch
Scanning files...
Found 245 files
Processing chunks...
████████████████████████████████ 100%
Indexed 1,234 chunks
Watching for changes...Background Mode
For long-running projects:
# Start in background
grepai watch --background
# Check status
grepai watch --status
# Stop when done
grepai watch --stopStep 5: Search Your Code
Now search semantically:
# Basic search
grepai search "authentication flow"
# Limit results
grepai search "error handling" --limit 5
# JSON output for scripts
grepai search "database queries" --jsonExample Output
Score: 0.89 | src/auth/middleware.go:15-45
──────────────────────────────────────────
func AuthMiddleware() gin.HandlerFunc {
return func(c *gin.Context) {
token := c.GetHeader("Authorization")
if token == "" {
c.AbortWithStatus(401)
return
}
// Validate JWT token...
}
}
Score: 0.82 | src/auth/jwt.go:23-55
──────────────────────────────────────────
func ValidateToken(tokenString string) (*Claims, error) {
token, err := jwt.Parse(tokenString, func(t *jwt.Token) (interface{}, error) {
return []byte(secretKey), nil
})
// ...
}Step 6: Analyze Call Graphs (Optional)
Trace function relationships:
# Who calls this function?
grepai trace callers "Login"
# What does this function call?
grepai trace callees "ProcessPayment"
# Full dependency graph
grepai trace graph "ValidateToken" --depth 3Complete Workflow Summary
# 1. Install (once)
brew install yoanbernabeu/tap/grepai
brew install ollama && ollama serve & && ollama pull nomic-embed-text
# 2. Setup project (once per project)
cd /your/project
grepai init
# 3. Index (run in background)
grepai watch --background
# 4. Search (as needed)
grepai search "your query here"
# 5. Trace (as needed)
grepai trace callers "FunctionName"Quick Command Reference
| Command | Purpose |
|---|---|
grepai init | Initialize project config |
grepai watch | Start indexing daemon |
grepai watch --background | Run daemon in background |
grepai watch --status | Check daemon status |
grepai watch --stop | Stop daemon |
grepai search "query" | Semantic search |
grepai search --json | JSON output |
grepai trace callers "fn" | Find callers |
grepai trace callees "fn" | Find callees |
grepai status | Index statistics |
grepai version | Show version |
Search Tips
Be descriptive, not literal:
- ✅ "user authentication and session management"
- ❌ "auth"
Describe intent:
- ✅ "where errors are logged to the console"
- ❌ "console.error"
Use English:
- Models are trained primarily on English text
- Works best with English queries
Next Steps
After mastering the basics: 1. Configure embeddings: See grepai-embeddings-* skills 2. Setup storage: See grepai-storage-* skills 3. Advanced search: See grepai-search-* skills 4. MCP integration: See grepai-mcp-* skills
Output Format
Successful quickstart:
✅ GrepAI Quickstart Complete
Project: /path/to/your/project
Files indexed: 245
Chunks created: 1,234
Embedder: Ollama (nomic-embed-text)
Storage: GOB (local file)
Try these searches:
- grepai search "main entry point"
- grepai search "database connection"
- grepai search "error handling"Related skills
How it compares
Use this onboarding skill before advanced GrepAI query skills when the CLI is not yet installed or indexed.
FAQ
How long does grepai-quickstart take?
grepai-quickstart is designed as a complete walkthrough from installation to first search in about five minutes, assuming terminal access and an existing code project to index.
How do you install GrepAI in grepai-quickstart?
grepai-quickstart documents brew install yoanbernabeu/tap/grepai on macOS and a curl-based install script for Linux/macOS alternatives before indexing the target repository.
Is Grepai Quickstart safe to install?
skills.sh reports 1 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.