graphify is a multimodal knowledge graph construction tool meticulously designed for AI Agents, deeply integrated within the Claude Code environment. It transforms diverse information sources—including code, documents, papers, images, and video links—into queryable, structured knowledge graphs, leveraging Claude Vision to intelligently extract core concepts and relationships. This tool dramatically enhances information retrieval efficiency, saving up to 71.5x tokens per query, and ensures cross-session graph persistence. With intelligent insights and automated synchronization, graphify empowers developers and researchers with efficient intelligent assistance and advanced knowledge management.
code-review-graph is an AI-assisted code review tool that builds a structural map of code using Tree-sitter and incrementally tracks changes to provide precise context to AI assistants via the Model Context Protocol (MCP). This approach significantly reduces token consumption by enabling AI models to read only the minimal set of files relevant to a change, rather than the entire codebase. It aims to solve the token waste problem in large repositories and monorepos, improving the efficiency and quality of AI code reviews.