ByteZone
Back to listClaim this project

DeusDataDeveloper tools

Codebase Memory MCP

codebase-memory-mcp

A high-performance MCP server that builds local persistent knowledge graphs for millisecond-latency code intelligence and structural queries.

  • Backend
  • Full stack
  • QA / Testing
  • AI coding
  • Automation
  • Data analysis
  • CLI
  • Web
  • Windows
  • macOS
  • Linux
  • Self-hostable
  • Runs locally
  • Docker supported
Open websiteView on GitHub
codebase-memory-mcp screenshot
Popularity
39.8k Stars
GitHub stars
Recent activity
8/21/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Addresses the inefficiency and high token consumption of AI coding agents when navigating large codebases due to context window limitations.

Practical value

Provides millisecond-level queries via a persistent local knowledge graph, significantly reducing file traversal and offering a visual interface for structural understanding.

Innovation / differentiation

Combines Tree-sitter AST parsing with hybrid LSP semantic analysis, supporting 158 languages and indexing infrastructure-as-code files into the knowledge graph.

Leverage potential

Operates as an MCP server compatible with multiple coding agents, using a unified daemon to coordinate multi-session resources and simplify integration.

Why now

Aligns with the surge in demand for deep codebase understanding in AI agents, offering a local-first approach that avoids cloud API dependencies and privacy concerns.

Community activity

In the last 90 days there were 645 new issues and 727 pull requests; the bounded issue/PR samples include 72 issue authors and 47 PR contributors, with 16 releases.

Maintainer responsiveness

The 100-issue window sample had a 55% close rate, and the 99-pull-request sample had a 52% merge rate. Maintainer-comment observations covered only 13% of that issue sample, so response rate and first-response speed are not reported.

47 contributors in PR sample16 releasesPR merge rate 52% · 99 sampled in window

Key highlights

  • Parse code across 158 languages using tree-sitter AST analysis
  • Provide 15 MCP tools for search, architecture, impact analysis, and dead code detection
  • Include a built-in 3D interactive knowledge graph visualization UI

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

Runs locally

Difficulty

Easy — follow the steps

Docker supportedSelf-hostableRuns locally
  1. 01Run the installation script on macOS or Linux to automatically configure the environment.
  2. 02Download and execute the installation script using PowerShell on Windows.
  3. 03Restart your coding agent and issue the command "Index this project".
  4. 04Launch the built-in 3D visualization UI by running codebase-memory-mcp --ui=true.

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine
  • People who prefer Docker deploys

More about it

codebase-memory-mcp is a code intelligence engine designed for AI coding agents. By parsing repositories into persistent knowledge graphs, it significantly reduces token consumption during code exploration. The tool runs entirely locally, supports a wide range of programming languages, and automatically configures itself for major MCP clients.

Sources

Each field shows its status and source — expand to review.

15 · Expand

  • capability tags

    Verified

    ai_coding, automation, data_analysis

    Source: admin_cms · cms editor · 8/20/2026

  • editor note

    Verified

    {"en":"This tool runs as a native binary without external APIs or language runtimes. Its core strength lies in deep AST parsing via tree-sitter, making it suitable for AI agent scenarios requiring frequent, large-scale codebase structural analysis.","zh":"该工具通过本地原生二进制文件运行，无需外部 API 或运行时环境。其核心优势在于利用 tree-sitter 进行深度 AST 解析，适合需要频繁进行大规模代码库结构分析的 AI 代理场景。"}

    Source: admin_cms · cms editor · 8/20/2026

  • how to use

    Verified

    {"steps":[{"en":"Run the installation script on macOS or Linux to automatically configure the environment.","zh":"在 macOS 或 Linux 上运行安装脚本以自动配置环境。"},{"en":"Download and execute the installation script using PowerShell on Windows.","zh":"在 Windows 上使用 PowerShell 下载并运行安装脚本。"},{"en":"Restart your coding agent and issue the command \"Index this project\".","zh":"重启你的 AI 编程代理，并向其发送“Index this project”指令。"},{"en":"Launch the built-in 3D visualization UI by running `codebase-memory-mcp --ui=true`.","zh":"通过运行 `codebase-memory-mcp --ui=true` 启动内置的 3D 可视化界面。"}],"installAt":"local","difficulty":"easy"}

    Source: admin_cms · cms editor · 8/20/2026

  • intro

    Verified

    {"en":"codebase-memory-mcp is a code intelligence engine designed for AI coding agents. By parsing repositories into persistent knowledge graphs, it significantly reduces token consumption during code exploration. The tool runs entirely locally, supports a wide range of programming languages, and automatically configures itself for major MCP clients.","zh":"codebase-memory-mcp 是一款专为 AI 编程代理设计的代码智能引擎。它通过将代码库解析为持久化的知识图谱，减少了 AI 探索代码库时的 Token 消耗。该工具完全在本地运行，支持多种主流编程语言，并能自动配置主流 MCP 客户端。"}

    Source: admin_cms · cms editor · 8/20/2026

  • Latest release

    Verified

    v0.10.8

    Source: GitHub API · latest_release=v0.10.8 · 8/21/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 8/21/2026

  • needs api key

    Verified

    No

    Source: admin_cms · cms editor · 8/20/2026

  • One-liner

    Verified

    {"en":"A high-performance MCP server that builds local persistent knowledge graphs for millisecond-latency code intelligence and structural queries.","zh":"高性能代码库知识图谱 MCP 服务器，通过本地持久化索引实现毫秒级代码结构查询与分析。"}

    Source: admin_cms · cms editor · 8/20/2026

  • Platforms

    Verified

    windows, macos, linux

    Source: admin_cms · cms editor · 8/20/2026

  • Category hint

    Inferred from materials

    code intelligence

    Source: description · High-performance code intelligence MCP server · 8/13/2026

  • product forms

    Verified

    cli, web

    Source: admin_cms · cms editor · 8/20/2026

  • role tags

    Verified

    backend, fullstack, qa

    Source: admin_cms · cms editor · 8/20/2026

  • supports docker

    Verified

    Yes

    Source: Repository file · dockerfile=true; compose=true · 8/21/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 8/20/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 8/20/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

spec-kit

An open-source CLI toolkit for Spec-Driven Development that guides AI coding agents through structured specification, planning, and code generation steps.

Same Developer tools categoryBoth support AI coding

claude-code

An agentic coding tool for the terminal that understands codebases, handles routine development tasks, explains code, and works with Git workflows.

Same Developer tools categoryBoth support AI coding

codex

OpenAI’s coding agent that runs locally, with terminal, IDE, and desktop-app entry points.

Same Developer tools categoryBoth support AI coding

CLI-Anything

A toolkit for generating and managing agent-callable CLIs for existing software, with CLI-Hub, generation workflows, and skill/plugin integrations.

Same Developer tools categoryBoth support AI coding

adk-python

Google’s open-source Python framework for defining, orchestrating, evaluating, and deploying single- and multi-agent workflows.

Same Developer tools categoryBoth support AI coding

llama.cpp

A lightweight LLM inference engine implemented in C/C++, supporting various hardware backends and model quantization.

Same Developer tools categoryBoth support AI coding