{"repo":"Abhishek-Aditya-bs/CodeGraph","free":true,"listed":false,"github":"https://github.com/Abhishek-Aditya-bs/CodeGraph","clone":"git clone https://github.com/Abhishek-Aditya-bs/CodeGraph.git","description":"GraphRAG over any codebase — a Neo4j knowledge graph of code entities plus a 3072-dim vector index, bridged so one natural-language query walks structure and ranks by meaning. Python · Neo4j · OpenAI embeddings · Streamlit · Docker. Hybrid semantic + structural code search.","language":"Python","stars":22,"topics":["code-search","docker","embeddings","graphrag","knowledge-graph","llm","neo4j","openai","python","rag"],"license":"MIT","category":"ai-agents","readme_excerpt":"CodeGraph turns any codebase into a Neo4j knowledge graph of its files, classes, functions and interfaces — then layers vector embeddings on top so you can ask it questions in plain English. Graph traversal and semantic search answer together, through a clean Streamlit interface. Website  ·  How it works  ·  Workflow  ·  Quick start  ·  Usage  ·  Architecture --- Overview Structure and meaning are different kinds of information. A call graph is topology; \"what does this module do \" is semantics. Keyword search and plain vector search each capture only one of them. CodeGraph keeps both and bridges them. It builds a knowledge graph of typed code entities and a semantic vector index over the same source, stores them in a single Neo4j database, and connects them with a bridge layer — so one natural-language question can walk relationships and rank by similarity in a single pass. - Hybrid GraphRAG — graph traversal combined with vector search, so structure and meaning inform every answer instead of competing. - One queryable database — the knowledge graph, the 3072-dimensional vector index, and file metadata all live in Neo4j. - Natural-language queries — ask in plain English and get answers grounded in real code, with the surrounding structure attached. - A real interface — a Streamlit app with live connection status, a step-by-step workflow tracker, and real-time feedback, not a notebook demo. - Configurable models — bring any Op","default_branch":null,"files":null,"tree":[],"storefront":"/r/Abhishek-Aditya-bs","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Abhishek-Aditya-bs/CodeGraph/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}