In Memoria
Builds persistent intelligence about your codebase by analyzing code patterns, architecture, and developer conventions, then provides this context to AI assistants across sessions so they remember your project's specifics.
What it does
- Analyze codebase structure and extract semantic patterns
- Search code by text matching or regex patterns
- Predict which files to modify for specific tasks
- Generate coding recommendations based on existing patterns
- Track developer conventions and architectural decisions
- Store and retrieve discovered insights across sessions
Best for
Tools (14)
One-time analysis of a specific file or directory. Returns AST structure, complexity metrics, and detected patterns for that path only. For project-wide understanding, use get_project_blueprint instead (faster, uses learned intelligence). Use this for deep-dive analysis of a specific file you're currently working on.
Search for code by text matching or patterns. Use "text" type for finding specific strings/keywords in code. Use "pattern" type for regex/AST patterns. Note: For "where should I work?" or "what files to modify?" questions, use predict_coding_approach instead - it provides intelligent file routing without exploration.
Build intelligence database from codebase (one-time setup, ~30-60s). Required before using predict_coding_approach, get_project_blueprint, or get_pattern_recommendations. Re-run with force=true if codebase has significant changes. Most users should use auto_learn_if_needed instead - it runs this automatically when needed.
Search for code-level symbols (variables, functions, classes) by name and see their relationships, usage patterns, and evolution. Use this to find where a specific function/class is defined, how it's used, or what it depends on. Searches actual code identifiers (e.g., "DatabaseConnection", "processRequest"), NOT business concepts or natural language descriptions.
Get coding pattern recommendations learned from this codebase. Use this when implementing new features to follow existing patterns (e.g., "create a new service class", "add API endpoint"). Returns patterns like Factory, Singleton, DependencyInjection with confidence scores and actual examples from your code. These patterns are learned from the codebase, not hardcoded - they reflect how THIS project does things.
