Abstract
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.
Abstract (translated)
大型语言模型（LLM）编码代理通常通过重复的文件读取和grep搜索来探索代码库，每次查询消耗数千个token却缺乏结构理解。我们提出Codebase-Memory，一个开源系统，它通过模型上下文协议（MCP）构建持久化的、基于Tree-Sitter的知识图谱，采用多阶段流水线并行工作池、调用图遍历、影响分析和社区发现来解析66种语言。在31个真实仓库的评估中，Codebase-Memory达到83%的答案质量，而文件探索代理为92%，但前者仅使用十分之一的token和2.1倍更少的工具调用。对于中心节点检测和调用者排名等图原生查询，它在31种语言中的19种上表现匹配或超过探索代理。
URL
https://arxiv.org/abs/2603.27277
