Scaffold

Scaffold parses source code across multiple programming languages using language-specific parsers (tree-sitter based) to extract Abstract Syntax Trees (ASTs). The system decomposes code into structural entities (files, classes, methods, functions) and captures their syntactic relationships, enabling downstream graph generation. This approach preserves code semantics rather than relying on regex or simple text analysis.

Scaffold persists parsed code structure into two complementary databases: PostgreSQL stores relational metadata (files, entities, timestamps, ownership) while Neo4j maintains the knowledge graph with semantic relationships (inheritance, method calls, imports, dependencies). This polyglot persistence strategy optimizes for both structured queries (SQL) and graph traversal operations (Cypher), enabling efficient context retrieval at scale. The system maintains bidirectional sync between databases to ensure consistency.

Scaffold provides a search interface that combines keyword matching with semantic and structural filtering. Users can search for code entities by name, type, or relationship (e.g., 'find all classes that inherit from BaseController'). The search engine leverages the knowledge graph to understand entity types, relationships, and context, enabling more precise results than simple text search. Results can be filtered by entity type, location, or relationship properties.

Scaffold monitors source code changes (via file system watchers or git hooks) and incrementally updates the knowledge graph without re-parsing the entire codebase. The system detects modified, added, and deleted files, re-parses only affected code, and updates both PostgreSQL and Neo4j with delta changes. This approach avoids expensive full re-indexing and enables near-real-time graph synchronization as developers commit code.

Scaffold provides a query interface (Cypher for Neo4j, SQL for PostgreSQL) to retrieve code entities and their relationships based on semantic context. Queries can traverse dependency graphs (e.g., 'find all functions called by this method'), retrieve related code (e.g., 'find all classes in the same module'), or identify architectural patterns (e.g., 'find all implementations of this interface'). Results are ranked by relevance and formatted as structured context suitable for LLM injection.

Scaffold implements the Model Context Protocol (MCP) standard, providing a standardized interface through which AI agents and LLMs can request code context without direct database access. The MCP layer exposes Scaffold's knowledge graph as a set of tools/resources (e.g., 'get_entity_context', 'find_related_code', 'get_dependency_graph') that agents can invoke via standard MCP messages. This abstraction decouples agents from Scaffold's internal architecture and enables multi-agent coordination.

Scaffold generates and maintains living documentation by extracting code structure, relationships, and patterns from the knowledge graph and synthesizing them into human-readable documentation. Unlike static docs, this documentation is automatically updated whenever code changes are indexed, ensuring it stays synchronized with the actual codebase. The system can generate architecture diagrams, dependency maps, API documentation, and module overviews directly from graph data.

Scaffold provides utilities to automatically inject relevant code context into LLM prompts based on the task at hand. Given a user query or code location, the system retrieves related entities from the knowledge graph and formats them as context (code snippets, signatures, relationships, documentation) that is prepended to the LLM prompt. This approach enables LLMs to understand codebase-specific patterns, conventions, and architecture without requiring the entire codebase in the prompt.

Scaffold represents code at multiple levels of abstraction—files, modules, classes, methods, functions, and variables—each with their own graph nodes and relationships. This hierarchical representation enables context retrieval at different granularities: asking for 'all methods in a class' vs. 'all functions in a file' vs. 'all callers of a specific method'. The system maintains parent-child relationships and scope information, enabling precise context selection based on the level of detail needed.

Scaffold analyzes code dependencies (imports, function calls, class inheritance, module references) and constructs a dependency graph that enables impact analysis. Given a code change, the system can identify all downstream dependents (what code depends on this entity) and upstream dependencies (what this entity depends on). This enables developers and AI agents to understand the blast radius of changes and identify affected code without manual analysis.

Scaffold analyzes the knowledge graph to detect common architectural patterns (e.g., MVC, dependency injection, factory pattern) and identify code smells (e.g., circular dependencies, god classes, unused code). The system uses graph-based heuristics (e.g., node degree, clustering coefficients, path lengths) to identify suspicious patterns that may indicate design issues. Results are surfaced as warnings or insights that developers and AI agents can act upon.