RepositoryGraphify-Labs/graphifyTool
Standard vector-based RAG frequently struggles with large software projects because it loses structural and relational context. A deterministic knowledge graph provides coding agents with exact architectural context, improving reasoning and reducing hallucinations.
Graphify addresses the shortcomings of embedding-based retrieval in AI code workflows. Rather than treating code as plain text chunks in a vector database, it extracts structural dependencies deterministically via AST parsing. The technology stack builds on Python, Tree-sitter, Leiden clustering, and MCP protocols. It is intended for software engineers using coding assistants such as Claude Code, Cursor, or Gemini CLI across non-trivial repositories. With more than 114,000 stars, over 11,000 forks on GitHub, and active package distribution via PyPI, the project demonstrates exceptionally high adoption and community maturity.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Link:graphify.net
Graphify is an open-source skill and MCP server that creates queryable knowledge graphs from source code, documentation, papers, and diagrams to help AI coding assistants understand multi-modal codebases.
Repository:abhigyanpatwari/GitNexus
GitNexus by Akon Labs indexes codebases into knowledge graphs, exposing architectural context via the Model Context Protocol (MCP) to AI coding tools like Cursor and Claude Code.
47kstarsTypeScript
Repository:DeusData/codebase-memory-mcp
codebase-memory-mcp is a pure C Model Context Protocol (MCP) server that indexes codebases into persistent knowledge graphs, providing AI coding agents with sub-millisecond structural search while dramatically reducing token consumption.
42.3kstarsC
Repository:tt-a1i/archify
Archify is an open-source Node.js rendering and validation engine designed as a skill for coding agents like Cursor, Claude Code, Codex CLI, and OpenCode. Agents produce a typed JSON Intermediate Representation (IR), which Archify deterministically compiles into self-contained, interactive HTML, SVG, and media exports.
45.5kstarsJavaScript
Article:Ravi Saive
codebase-memory-mcp is a standalone C-based MCP backend that indexes codebases into a local SQLite knowledge graph using tree-sitter, drastically cutting token consumption and latency for AI coding agents.
X post:Marco Ramilli
Marco Ramilli highlights Archify, an open-source skill for coding agents like Claude Code, Cursor, and Codex that turns codebases or system concepts into interactive HTML diagrams.
1.1kbookmarks80.3kviews
Parts of this content were created with the assistance of AI.
