colbymchenry/codegraph
Codegraph
Codegraph is a local codebase indexer and static analysis graph database that serves as a context provider for AI agents. It parses multiple programming languages into a searchable knowledge graph of symbols and dependencies, exposing these relationships to AI tools through the Model Context Protocol.
The project distinguishes itself by aggregating relevant code snippets and symbol flows to reduce token usage for large language models. It automates the configuration of server settings and steering instructions across various AI agent platforms and command line editors to enable automatic codebase navigation.
The system covers broad capability areas including transitive dependency impact analysis, execution flow tracing, and framework route mapping. It utilizes a background daemon for incremental parsing and filesystem synchronization, ensuring the local symbol database remains current across multi-repo workspaces.
The application is delivered as a self-contained bundle to ensure environment consistency on host systems.
Features
- Model Context Protocol - Implements the Model Context Protocol to expose source code relationships and symbol flows to AI automation tools.
- Codebase Indexing - Provides local knowledge graphs and symbol maps to AI agents to reduce token usage and improve codebase understanding.
- Agent Context Providers - Dynamically aggregates symbols and code snippets to provide essential implementation context to AI agents.
- AI Agent Integrations - Provides connectors and configuration interfaces to integrate AI coding assistants and editors with the codebase.
- Codebase Impact Analysis - Traces transitive dependencies and import chains to identify which tests or functions are affected by specific code changes.
- Codebase Dependency Mapping - Analyzes call paths, imports, and inheritance to map symbol dependencies across multiple programming languages.
- Knowledge Graph Construction - Indexes source code across multiple languages into a local graph to enable fast symbol lookup and relationship tracing.
- Code Impact Analysis - Traverses the knowledge graph to identify the full blast radius of a change by tracing callers and callees.
- Static Analysis Databases - Provides a database of code structures that enables impact analysis and transitive dependency tracing across repositories.
- Code Relationship Mappers - Traverses the knowledge graph to identify callers, callees, and the impact radius of code changes.
- Model Context Protocol Servers - Acts as an MCP server that exposes a structured graph of code flows and symbols to AI agents.
- Knowledge Graph Indexers - Parses source files into a searchable knowledge graph of symbols and edges using incremental updates.
- Deterministic Symbol Indexing - Creates a consistent map of symbols and edges across multiple languages for accurate and repeatable symbol resolution.
- Code Knowledge Graphs - Exposes a local index of source code symbols and relationships to AI agents via the Model Context Protocol.
- Local-First Databases - Stores code relationships and definitions in a local database to enable fast querying without network requests.
- Symbol Resolution - Generates symbols and edges for multiple languages using incremental parsing to create a structured map of source code.
- Static Code Analysis - Maps dependencies, call graphs, and symbol relationships across multiple programming languages to understand complex software structures.
- Change Impact Analysis - Identifies the blast radius of a change by surfacing all symbols that depend on a modified constant or function.
- AI-Consumable Graph Formats - Formats complex graph data into markdown or JSON to ensure AI agents can efficiently consume codebase relationships.
- Search Index Synchronizers - Monitors the filesystem for changes and triggers index updates to keep the internal data graph current.
- Code Exploration Tools - Returns relevant source code for symbols while collapsing redundant implementations to optimize agent context.
- Test Dependency Analysis - Traces import dependencies transitively to identify which test files are affected by changes to specific source files.
- Daemon Management - Employs a background daemon to handle indexing and synchronization, preventing redundant resource usage.
- Language Bridges - Connects execution flows across language boundaries, such as bridging high-level scripts to native modules.
- Execution Flow Analyzers - Follows request-to-handler paths and bridges gaps in dynamic dispatch, such as callbacks and event emitters.
- Framework Integration - Maps indirect calls and routes by applying heuristic patterns for specific software frameworks.
- Filesystem Event Synchronization - Monitors the local file system for changes to trigger targeted updates of the knowledge graph.
- Route Handlers - Identifies routing files and maps URL patterns to their corresponding handler functions or classes.
- Heuristic Route Resolution - Applies language-specific patterns to link URL definitions in routing files to their handler functions and classes.
