Overview
CodeAlive’s semantic code search goes beyond keyword matching — it understands the meaning and intent behind your queries. Ask for “authentication flow” and find JWT validation, OAuth callbacks, and session management code, even if none of those files contain the word “authentication.” This is powered by CodeAlive’s GraphRAG indexing, which maps relationships between code components, dependencies, and architectural patterns across your entire codebase.How It Works
Index
CodeAlive indexes your repositories, building a knowledge graph of code relationships, function signatures, data flows, and architectural patterns.
Query
You ask a natural-language question. CodeAlive translates it into a semantic search across the knowledge graph, finding code that matches by meaning — not just text.
Search Modes
- Auto (Default)
- Fast
- Deep
Intelligent semantic search that balances speed and thoroughness. Use this 80% of the time.
Example Queries
Authentication & Security
Authentication & Security
- “How is JWT token validation implemented?”
- “Find OAuth callback handlers”
- “Show me all authorization middleware”
- “Where are API keys validated?”
Error Handling
Error Handling
- “How does the system handle database connection failures?”
- “Find retry logic across services”
- “Show me error boundary implementations”
- “Where are 500 errors caught and reported?”
Architecture Patterns
Architecture Patterns
- “Find all event-driven communication between services”
- “Show me the repository pattern implementations”
- “How is dependency injection configured?”
- “Find all middleware in the request pipeline”
API & Data
API & Data
- “List all REST API endpoints”
- “Find database migration files”
- “Show me GraphQL resolver implementations”
- “Where is caching implemented?”
Access Methods
- MCP Tool
- REST API
- Skill CLI
The
Your AI agent calls this tool automatically when you ask questions about your codebase.
codebase_search tool is available through any CodeAlive-connected agent:| Parameter | Required | Description |
|---|---|---|
query | Yes | Natural-language search query |
data_sources | Yes | Repository or workspace names to search |
mode | No | auto (default), fast, or deep |
Best Practices
Be Specific
Use domain-specific terms: “JWT validation” is better than “security check”
Start with Auto
Use auto mode first. Switch to deep only for complex cross-cutting queries
Scope Your Search
Target specific repositories or workspaces to get more relevant results
Iterate
Refine your query based on initial results — each search is fast and cheap