一个持久化、由 Git 版本管理的全代码库与数据库 schema 地图,编码智能体在动手修改任何内容之前会先读取它。用 Go 编写的本地优先 MCP 服务器 + CLI:一个受治理的代码知识仓库索引,为 Claude Code、Codex、Cursor 和 opencode 提供长期上下文、记忆和代码智能。
code-indexing 开源项目推荐(86 个)
code-indexing 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 86 个仓库本地代码智能MCP服务器和AI编码代理的CLI
可节省 94% 的 AI 编程 token。为代码库建立索引,agent 通过搜索而不是读取文件。兼容 Claude Code、Codex、Copilot、Cursor、Gemini CLI。本地 MCP 服务器,免费,开源。
CodeGraph构建了你的代码库——函数、类、导入、调用链——的语义图,并通过42个MCP工具、38种语言、VS Code扩展和持久内存层展开。AI代理能理解结构化的代码,而不是逐一浏览文件。
为AI代理提供深度代码索引MCP服务器。25个工具:混合FTS5 + 嵌入搜索、呼叫图、git blame/hotspots、构建系统分析。多仓库工作区、GPU加速语义搜索、通过树置工具支持10种语言。完全本地化,零云依赖。
A Repository-Aware, Knowledge-Learning local MCP that understands your codebase in Real Time powered by Hybrid Semantic + Full-Text Engine, both supports claude code and codex
MCP Server for persistent code indexing. Gives AI assistants (Claude, Gemini, Copilot, Cursor) instant access to your codebase. 50x less context than grep.
Convert source code to LLM ready knowledge base
Vim 风格的 TUI,具备仓库感知、能自我进化的智能体,可实时理解代码库,由混合语义 + 全文检索引擎驱动
A semantic code search tool for intelligent, cross-repo context retrieval.
Understand millions of lines of code locally. Eulix builds structural and semantic indexes for fast code navigation and retrieval.
Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.
Give Claude Code a permanent memory — 100% local, zero config, graph-powered
Ultra-fast file search toolkit for AI agents, Neovim, and code editors. MCP server for Claude Code/Cursor/Codex, frecency-ranked search, symbol indexing via tree-sitter, and a Rust core that outperforms ripgrep and fzf in long-running processes.
High-performance Rust MCP server & CLI codebase indexer for AI agents. Unlocks deep codebase understanding through semantic vector search, structural graph traversal, and cross-repo dependency resolution. Empowers AI coding agents with semantic and structural search for maximum token efficiency.
Memory-aware context engine for AI coding agents — up to 91% fewer tokens, 17/18 rank-1 across 6 OSS projects. MCP-native, multi-repo, with persistent observations & decisions.
Go-based MCP server for codebase indexing and semantic search (Augment-compatible)
Evidence before edits. Local repository intelligence for AI coding agents: the right files with proof, a bounded plan, and a verified diff. Measured nightly on real repositories.
Lightweight persistent memory for Claude Code — SQLite + FTS5, no daemon, no bloat. Session summaries, code indexing, task tracking, and contextual memory injection.
Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/code-indexing。
- 该话题在 GitHub 上共有 86 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 3652 Star,覆盖 7 种主要语言,数据更新于 2026-11-12。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。