Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP
Large Language Model (LLM) coding agents typically explore codebases through repeated file-reading and grep-searching, consuming thousands of tokens per query without structural understanding. We present Codebase-Memory, an open-source system that constructs a persistent, Tree-Sitter-based knowledge graph via the Model Context Protocol (MCP), parsing 66 languages through a multi-phase pipeline with parallel worker pools, call-graph traversal, impact analysis, and community discovery. Evaluated across 31 real-world repositories, Codebase-Memory achieves 83% answer quality versus 92% for a file-exploration agent, at ten times fewer tokens and 2.1 times fewer tool calls. For graph-native queries such as hub detection and caller ranking, it matches or exceeds the explorer on 19 of 31 languages.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsSimilar Papers 제목 키워드 기반
Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs
Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as controller to service to repos…
Graph GenerationKnowledge GraphsDesign and Control of a Coaxial Dual-rotor Reconfigurable Tailsitter UAV Based on Swashplateless Mechanism
The tailsitter vertical takeoff and landing (VTOL) UAV is widely used due to its lower dead weight, which eliminates the actuators and mechanisms for tilting. However, the tailsitter UAV is susceptible to wind disturbanc…
Implementation of a neural network for non-linearities estimation in a tail-sitter aircraft
The control of a tail-sitter aircraft is a challenging task, especially during transition maneuver where the lift and drag forces are highly nonlinear. In this work, we implement a Neural Network (NN) capable of estimate…
BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice
As enterprise codebases continue to grow in scale and complexity, the volume of lint errors far exceeds engineers' manual remediation capacity, leading to continuous accumulation of technical debt and hindered developmen…
Reinforcement LearningCOMEX: A Tool for Generating Customized Source Code Representations
Learning effective representations of source code is critical for any Machine Learning for Software Engineering (ML4SE) system. Inspired by natural language processing, large language models (LLMs) like Codex and CodeGen…
Representation Learning