safishamsi/graphify
Graphify
Graphify is a knowledge retrieval system that transforms directories of source code and documentation into structured, queryable project maps. It utilizes a code-to-graph parser to extract technical metadata and system connectivity, converting a mix of code, SQL schemas, and documentation into a unified graph structure.
The project distinguishes itself by integrating these knowledge graphs with AI coding assistants through a Model Context Protocol server and dedicated tool hooks. This allows AI agents to perform lookups and impact analysis on node neighbors and shortest paths to understand how code changes affect a system.
The system includes a network layer that hosts the project intelligence as a shared service via an HTTP API for multi-user remote access. It also provides configuration utilities to manage extraction boundaries using ignore patterns to exclude specific files and reduce graph noise.
Features
- Codebase Dependency Mapping - Transforms folders of source code and documentation into queryable graphs to analyze system architecture and dependencies.
- Code-to-Graph Parsers - Transforms directories of source code and documentation into a structured, queryable knowledge graph for project mapping.
- Graph-Based Context Providers - Streams structured graph entities and relationships into AI agent prompts via the Model Context Protocol.
- AI Coding Assistant Integrations - Connects knowledge graphs to AI agents via Model Context Protocol to provide structured project context during development.
- Technical Asset Normalizers - Transforms diverse inputs including code, SQL schemas, and documentation into a unified and queryable graph structure.
- MCP Servers - Implements an MCP server that transforms source code and documentation into a queryable knowledge graph for AI agents.
- Architectural Change Impact Analysis - Uses graph data to perform lookups on node neighbors and shortest paths to analyze how code changes affect the system.
- AI Coding Assistants - Integrates with AI agents to provide critical project context through graph-based impact analysis and lookups.
- Model Context Protocol Integrations - Integrates with AI agents using the Model Context Protocol to stream structured graph data for impact analysis.
- Technical Concept Extraction - Parses source code and documentation to identify technical metadata and system connectivity for the project map.
- Connectivity Extractors - Parses source code and documentation to identify technical concepts and system connectivity for conversion into a knowledge graph.
- AI Coding Assistant Configurations - Provides configuration profiles and tool hooks to prompt AI agents to query the knowledge graph before accessing source files.
- Knowledge Graph APIs - Implements an HTTP API that exposes the project knowledge graph as a shared network service for remote access.
- Agent Configurations - Injects local configuration files and hooks into AI assistants to trigger graph-based retrieval.
- Design Rationale Extractors - Extracts core concepts and design rationale from a mix of code, papers, and scripts into a structured format.
- Centralized Project Intelligence - Hosts a centralized knowledge graph over HTTP so multiple team members can query a single source of project truth.
- Multi-User Graph Hosting - Allows the knowledge graph to be served over HTTP for multi-user query access from a single shared process.
- Remote Access APIs - Exposes the internal project knowledge graph as a shared network service allowing remote queries via standard web requests.
- AI and Agents - Turn any folder of code, SQL schemas, docs, papers, images, or videos into a queryable knowledge graph.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
