📄 工具详情 ⚙️ 安装教程 📚 使用教程
能力标签
🔌 MCP🤖 Agent🔄 工作流👁 OCR🐳 Docker💻 CLI🔗 REST API🧬 Embedding🖼 视觉🧠 Claude
lilbee MCP工具
🔌
MCP工具

lilbee MCP工具

基于 Python · 让 AI 助手直接操作你的系统与工具
英文名：lilbee
⭐ 18 Stars 🍴 3 Forks 💻 Python 📄 NOASSERTION 🏷 AI 7.2分
7.2AI 综合评分
本地搜索文档对话网页爬虫向量嵌入终端工具
⚙️ 配置说明 📺 TG 频道
✦ AI Skill Hub 推荐

lilbee MCP工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.2 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。

📚 深度解析

lilbee MCP工具 是一款基于 MCP（Model Context Protocol）标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源，旨在建立 AI 模型与外部工具之间的标准化通信接口，目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 lilbee MCP工具，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。lilbee MCP工具 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 lilbee MCP工具 评为 AI 评分 7.2 分，属于同类工具中的优质选择。

📋 工具概览

lilbee MCP工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

GitHub Stars
⭐ 18
开发语言
Python
支持平台
Windows / macOS / Linux
维护状态
轻量级项目，按需更新
开源协议
NOASSERTION
AI 综合评分
7.2 分
工具类型
MCP工具
Forks
3

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

lilbee MCP工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

📌 核心特色
  • 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
  • 提供结构化工具调用接口，显著降低 AI 集成复杂度
  • 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
  • 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
  • 轻量无侵入设计，不影响现有系统架构
🎯 主要使用场景
  • 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
  • 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。
安装命令
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/tobocop2/lilbee

# 方式二：手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "lilbee-mcp--": {
      "command": "npx",
      "args": ["-y", "lilbee"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
📋 安装步骤说明
  1. 确认已安装 Node.js（v18 或以上版本）
  2. 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
  3. 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
  4. 保存配置文件并重启 Claude 客户端
  5. 重启后，在对话中即可使用本工具
以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。
常用命令 / 代码示例
# 安装后在 Claude 对话中直接使用
# 示例：
用户: 请帮我用 lilbee MCP工具 执行以下任务...
Claude: [自动调用 lilbee MCP工具 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入："列出所有可用的 MCP 工具"
以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。
配置示例
// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "lilbee_mcp__": {
      "command": "npx",
      "args": ["-y", "lilbee"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效
📑 README 深度解析 真实文档 完整度 82/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

<p align="center"> <a href="https://lilbee.sh/"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/tobocop2/lilbee/main/docs/lilbee-logo-dark.svg"> <img alt="lilbee" src="https://raw.githubusercontent.com/tobocop2/lilbee/main/docs/lilbee-logo-light.svg" width="340"> </picture> </a> </p>

<p align="center"><strong>Run and manage local AI models, and search everything you own with them, all in one program.</strong></p>

<p align="center"><a href="https://lilbee.sh/">Project site</a> &nbsp;·&nbsp; <a href="https://lilbee.sh/tutorial">Tutorial reels</a> &nbsp;·&nbsp; <a href="https://pypi.org/project/lilbee/">PyPI</a> &nbsp;·&nbsp; <a href="https://obsidian.lilbee.sh/">Obsidian plugin</a> &nbsp;·&nbsp; <a href="https://lilbee.sh/api/">REST API</a></p>

<p align="center"> <a href="https://github.com/tobocop2/lilbee/releases"><img src="https://img.shields.io/github/v/release/tobocop2/lilbee?include_prereleases&label=release&logo=github&logoColor=white" alt="Latest release"></a> <a href="https://pypi.org/project/lilbee/"><img src="https://img.shields.io/pypi/v/lilbee?include_prereleases&label=PyPI&logo=pypi&logoColor=white" alt="lilbee on PyPI"></a> <a href="https://www.python.org/downloads/"><img src="https://img.shields.io/badge/python-3.11%2B-3776AB?logo=python&logoColor=white" alt="Python 3.11+"></a> <img src="https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey" alt="Platforms"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-2C3E50" alt="License: MIT"></a> <a href="https://community.obsidian.md/plugins/lilbee"><img src="https://img.shields.io/badge/Obsidian-Community%20plugin-7c3aed?logo=obsidian&logoColor=white" alt="Obsidian community plugin"></a> <a href="https://glama.ai/mcp/servers/tobocop2/lilbee"><img src="https://glama.ai/mcp/servers/tobocop2/lilbee/badges/score.svg" alt="Glama MCP server score"></a> </p>

<p align="center"> <a href="https://github.com/tobocop2/lilbee/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/tobocop2/lilbee/ci.yml?branch=main&label=CI&logo=githubactions&logoColor=white" alt="CI"></a> <a href="https://lilbee.sh/coverage/"><img src="https://img.shields.io/badge/coverage-100%25-2EA043" alt="Coverage"></a> <a href="https://mypy-lang.org/"><img src="https://img.shields.io/badge/typed-mypy-2A6DB2" alt="Typed"></a> <a href="https://github.com/astral-sh/ruff"><img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff"></a> <a href="https://pepy.tech/project/lilbee"><img src="https://img.shields.io/pepy/dt/lilbee?label=downloads&logo=python&logoColor=white&color=3776AB" alt="PyPI downloads"></a> <a href="https://github.com/tobocop2/lilbee/releases"><img src="https://img.shields.io/github/downloads/tobocop2/lilbee/total?label=release%20downloads&logo=github&logoColor=white&color=2C3E50" alt="GitHub release downloads"></a> </p>

<p align="center"> <a href="https://pypi.org/project/lilbee/"><img src="https://img.shields.io/badge/PyPI-pip%20%7C%20uv-3775A9?logo=pypi&logoColor=white" alt="Install from PyPI"></a> <a href="https://github.com/tobocop2/homebrew-lilbee"><img src="https://img.shields.io/badge/Homebrew-tap-FBB040?logo=homebrew&logoColor=white" alt="Homebrew tap"></a> <a href="https://aur.archlinux.org/packages/lilbee"><img src="https://img.shields.io/aur/version/lilbee?logo=archlinux&logoColor=white&label=AUR" alt="lilbee on the AUR"></a> <a href="https://github.com/tobocop2/lilbee/pkgs/container/lilbee"><img src="https://img.shields.io/badge/Docker-ghcr.io-2496ED?logo=docker&logoColor=white" alt="Docker image on GHCR"></a> </p>

<p align="center"> <a href="https://github.com/tobocop2/lilbee#install"><img src="https://img.shields.io/badge/Nix-flake-5277C3?logo=nixos&logoColor=white" alt="Nix flake"></a> <a href="https://tobocop2.github.io/flatpak-lilbee/"><img src="https://img.shields.io/badge/Flatpak-repo-4A90D9?logo=flatpak&logoColor=white" alt="Flatpak repo"></a> <a href="https://github.com/tobocop2/lilbee/releases/latest"><img src="https://img.shields.io/badge/Snap-sideload-82BEA0?logo=snapcraft&logoColor=white" alt="Snap package"></a> <a href="https://github.com/tobocop2/lilbee#install"><img src="https://img.shields.io/badge/Scoop-bucket-555555?logo=windows&logoColor=white" alt="Scoop bucket"></a> </p>

A batteries-included local search engine you can talk to: it runs the AI models, indexes your files and code, crawls the web, and plugs into your coding agent, so there's nothing else to install or set up. Ask in plain English; every answer cites the file and line.

ask lilbee "what is lilbee in one sentence?" and get a cited answer drawn from its own README

It's all one program: no separate model server, vector database, or container to stand up. lilbee runs the models and keeps the index itself. Reach it as a terminal app, CLI, Model Context Protocol server, HTTP API, or Python library. Close it and it's gone, or run it as a service to keep it warm. Everything runs on your computer; it uses a cloud model only when you pick one.

Models are no different: lilbee has its own model manager and multi-GPU fleet, built on llama.cpp, so one executable does everything (browse Hugging Face, download a model, give it a role, run it on Metal / Vulkan / CUDA). Battle-tested managers are always supported too. If you already use Ollama or LM Studio, point lilbee at your existing setup and skip its native model support if you prefer.

Tutorial reel: every demo on this page (and the extras) as a real video player at lilbee.sh/tutorial.
## ⚠️ Beta software lilbee is in active beta development. Every release on PyPI is a pre-release; you must use --pre (or uv's --prerelease=allow) when installing. Interfaces, command names, and on-disk formats may shift between betas. Feedback, bug reports, and issues are very welcome; that's the whole point of the beta. Latest pre-release (always): lilbee on PyPI →

---

---

Highlights

  • Answers cite the source line. Click a citation, jump to the file at the exact line. When the answer isn't in your library, lilbee says so instead of inventing one.
  • It works, and the demos prove it. Every GIF and tutorial reel here is recorded live on real hardware, nothing staged. Backed by 100% test coverage, full typing, and CI on macOS, Linux, and Windows.
  • Up and running in one command. Install, run lilbee, and a first-run wizard pulls a model and drops you straight into chat.
  • Reads almost anything you point it at. Documents, scanned pages, spreadsheets, ebooks, web pages, and source code: 90+ formats and 150+ languages in all. Whatever you give it becomes searchable.
  • Splits it into pieces that stand on their own. Prose and code are chunked differently, so each piece keeps its meaning instead of getting cut mid-thought. A search engine is only as good as the chunks underneath it, and this is where most of the quality lives.
  • A sophisticated search engine on top, built on published research. It ranks every result by how well it answers you, so the best match comes back first. 50+ knobs to tune from the Settings screen or hand to your agent, with sane defaults if you'd rather not.
  • It brings and runs the models itself. Browse Hugging Face, pull a model, give it a role (chat, embedding, vision, reranking); lilbee runs it on Metal, Vulkan, or CUDA. You never point it at a server you set up.
  • Already on Ollama or LM Studio? Keep them. Managing models for you is the default, but lilbee also works with both, so you never have to switch model managers. Their models show up in the same catalog and role pickers, alongside lilbee's own.
  • Your hardware, put to work. Your machine can do a lot more than you're using it for. lilbee runs local models on hardware you already own, no cloud account required.
  • Per-project libraries. Keep one library for everything, or give each project its own.
  • One install, many surfaces. TUI, CLI, MCP server, REST API, and Python library. Nothing to stand up.
  • Everything in one file, nothing to operate. The standalone binary bundles the whole thing (search engine, web crawler, MCP server, HTTP server, terminal UI, Python, and llama.cpp) in 250-365 MB, or 600 MB+ with CUDA. No Docker, no vector database, no model server, nothing to keep running; it loads on demand. Comparable desktop AI apps (often Electron) ship hundreds of MB to several GB and do less.
  • Works with your coding agent. Connect lilbee to your AI coding assistant and it answers from your actual files and code, with citations, instead of guessing. It can even adjust its own search as it works.

Hardware requirements

Standalone mode runs entirely on your machine. No cloud required. Minimum: Apple Silicon Mac, or a 64-bit Intel/AMD CPU from 2013+ (older CPUs: On older CPUs), or an ARMv8 Linux box; 8 GB RAM, 2 GB disk.

<details> <summary>Full platform and resource breakdown</summary>

PlatformMinimumRecommended
**macOS arm64**Apple Silicon (M1 or newer), macOS 11+M-series Pro / Max / Ultra
**Linux x86_64**64-bit Intel/AMD from 2013+ ([x86-64-v3](https://en.wikipedia.org/wiki/X86-64#Microarchitecture_levels))Modern Intel/AMD CPU + an NVIDIA, AMD, or Intel Arc GPU
**Windows x86_64**64-bit Intel/AMD from 2013+ (x86-64-v3), Windows 10/11Modern desktop / workstation CPU + GPU
**Linux ARM64**ARMv8 NEON-capable (Raspberry Pi 4+, AWS Graviton, Ampere Altra)Modern ARM server with 16+ GB RAM
ResourceMinimumRecommended
**RAM**8 GB16 to 32 GB to keep several local models warm at once (chat + embed + rerank + vision); actual footprint scales with the sizes and quantizations you pick
**GPU / Accelerator**none required (CPU-only works)Apple Silicon (Metal) · NVIDIA / AMD / Intel Arc (Vulkan) · NVIDIA + CUDA toolkit (opt-in CUDA wheels, see [Install](#install))
**Disk**2 GB10+ GB for multiple models

</details>

Linux runtime requirements

The Linux x86_64 wheel and binary link the Vulkan loader at runtime. Most desktop distros (Ubuntu 22.04+, Pop!\_OS, Mint) ship libvulkan1; bare Arch / Fedora / Alpine images don't, and lilbee self-check fails with cannot open shared object file: libvulkan.so.1. Install it once: sudo pacman -S vulkan-icd-loader (Arch / Manjaro), sudo dnf install vulkan-loader (Fedora, RHEL), or sudo apt-get install libvulkan1 (Debian, Ubuntu).

Already using an MCP-aware agent? Hand setup to it.

If you've already got an MCP-aware coding agent running, it can do the setup: browse the catalog, pull picks, assign them to the embedding / reranker / vision roles, and tune retrieval. No TUI, no config file, no restart. Agents already understand search engines, so the right knobs are obvious to them. See the lilbee-mcp skill for the workflow and example prompts.

Install

Two routes, and the difference matters:

  • Into your own Python with pip or uv (Python 3.11 to 3.14). Uses the Python and tooling you already have, picks the fastest CPU code path for your machine at runtime, and upgrades like any other package. Recommended if you have Python.
  • A self-contained bundle: the standalone binary, or the Homebrew / AUR / Nix / Docker / Flatpak / Snap builds that wrap it. Nothing else to install. The trade-off is a single large download (it bundles its own Python runtime, llama.cpp, and the optional extras) and a small cold-start cost the first time it self-extracts. Recommended if you'd rather not deal with Python.

Have an NVIDIA GPU? Both routes have a CUDA build that's faster than the default Vulkan path. Skip to On NVIDIA hardware.

No external services either way; lilbee downloads and runs models locally. Optional, for scanned-PDF / image OCR: Tesseract (brew install tesseract / apt install tesseract-ocr) or a GGUF vision model.

HowCommandNotes
**pip**pip install --pre lilbeeRecommended. The default wheel runs on any x86_64 CPU with AVX2 (2013+; older CPUs: [On older CPUs](#on-older-cpus-pre-avx2)) and uses your GPU via Vulkan / Metal automatically. Intel Mac: add --extra-index-url https://lilbee.sh/cpu/ ([browse wheels](https://lilbee.sh/cpu/lilbee/)).
**uv**uv tool install --prerelease=allow lilbeeSame wheel as pip; fetches a Python for you if you need one.
**Homebrew**brew tap tobocop2/lilbee && brew install lilbeemacOS arm64 / Linux x86_64. Bundled build; clears the macOS quarantine flag for you.
**AUR**paru -S lilbeeArch Linux. Wraps the Linux x86_64 binary; works with yay / pacaur / any helper.
**Docker**docker run --rm -v lilbee-data:/home/lilbee/data ghcr.io/tobocop2/lilbee:latest --helpGHCR image, tagged by version and latest. Data lives at /home/lilbee/data. Mount a volume there.
**Nix**nix run github:tobocop2/lilbeeNixOS, nix-darwin, or any host with nix. On Linux the flake bundles glibc, libgomp, and vulkan-loader so it runs on bare NixOS.
**Flatpak**flatpak remote-add --if-not-exists lilbee https://tobocop2.github.io/flatpak-lilbee/lilbee.flatpakrepo && flatpak install lilbee io.github.tobocop2.lilbeeLinux x86_64, any distro with flatpak. Needs the [Flathub remote](https://flathub.org/setup) for the runtime. Run with flatpak run io.github.tobocop2.lilbee (worth an alias); flatpak update picks up new releases. Data lives under ~/.var/app/io.github.tobocop2.lilbee/.
**Snap**curl -LO https://github.com/tobocop2/lilbee/releases/latest/download/lilbee-linux-x86_64.snap && sudo snap install ./lilbee-linux-x86_64.snap --dangerous --classicLinux x86_64. Sideloaded, so snapd flags it --dangerous (it just means unsigned) and it won't auto-update; rerun the same command to upgrade.
**Scoop**scoop bucket add lilbee https://github.com/tobocop2/lilbee && scoop install lilbeeWindows x86_64. Installs the CUDA build on machines with a recent NVIDIA driver, otherwise the CPU build. scoop update lilbee upgrades.
**Standalone binary**[download for your platform &rarr;](https://github.com/tobocop2/lilbee/releases/latest)One file, own Python runtime, no pip needed. Linux needs glibc 2.28+; the macOS / Windows builds are unsigned (xattr -d com.apple.quarantine ./lilbee-macos-arm64 if Gatekeeper blocks it).
**From source**git clone https://github.com/tobocop2/lilbee && cd lilbee && uv sync && uv run lilbeeFor hacking on it. Needs git and uv.

Quick start

Two recommended ways to use lilbee, depending on whether you're the one driving:

  • Run lilbee for the full-screen terminal app. A welcome wizard picks a chat and embedding model, then you index files, search, and chat without leaving the TUI. The Settings screen exposes every retrieval knob (search depth, distance threshold, reranker, chunking) so you can tune lilbee to your library shape.
  • Connect it to your agent over MCP. Any MCP-aware coding agent calls lilbee_search / lilbee_add and gets back cited snippets it can quote. Agents can also fine-tune lilbee on the fly via lilbee_settings_set. Drop in the lilbee-mcp skill and the agent reads the full surface: every tool, every retrieval knob, and when to widen for prose vs narrow for code. See Agent integration.

Defaults are sane for chatting with code, documentation, crawled sites, and long PDFs. Every retrieval setting is writable from the TUI Settings screen, the /set slash command, MCP lilbee_settings_set, or config.toml. When answers feel thin or noisy, the usual knobs are top_k, max_distance, or diversity_max_per_source.

CLI, the HTTP API, env vars, and config.toml are there for scripting, headless runs, and custom integrations. See the usage guide.

Optional extras

These only matter for a pip or uv install: add the name in brackets, e.g. pip install --pre 'lilbee[crawler,litellm]' (combine multiple, and --extra-index-url still works for CUDA). The standalone binary and the Homebrew / AUR / Nix / Docker / Flatpak / Snap builds already include all three. lilbee works without them either way.

ExtraWhat it adds
[crawler]Index websites alongside your files: crawl a docs site or wiki to markdown, then search it offline.
[litellm]Bridge to hosted model providers for chat, vision, or embeddings while other roles stay local. The TUI flags when a hosted role is active.
[graph]Concept-graph search: extracts the ideas in your documents and uses how they relate to surface matches plain keyword search misses. No extra model calls.

See the full guide on optional extras for configuration.

Running as a service (optional)

For tools that talk to lilbee's HTTP REST API (the Obsidian plugin, custom GUIs, anything hitting /api/*), your OS launcher can keep the HTTP server warm so requests skip the cold-start.

<details> <summary>Daemon setup per platform</summary>

This is the only lilbee surface that benefits from a daemon. The TUI, lilbee chat, the MCP server, and the rest of the CLI load on demand and exit when you close them. No always-on process to babysit.

Pull a chat and embedding model first; all recipes pin the server to 127.0.0.1:42697.

PlatformCommand
**macOS (Homebrew)**brew services start lilbee
**Linux (Arch / AUR)**systemctl --user enable --now lilbee (add loginctl enable-linger $USER on headless servers)
**NixOS**Import lilbee.nixosModules.lilbee, set services.lilbee.enable = true;

</details>

A reference for AI agents

Once configured, lilbee plugs into whatever agent you use, over MCP. Feed it your project's docs, your dependency source, your API docs, your design notes; the agent stops making up function names and instead reads the actual code, cites file and line, and says it doesn't know when the answer isn't in your library.

Your files, the search index, and the embeddings stay on your computer. The agent calls lilbee_search and gets back cited snippets. The demo below is lilbee talking to lilbee: an agent indexes lilbee's own source, then answers questions about how lilbee works with file:line citations.

an agent indexes lilbee's own source through lilbee's MCP server, then answers questions about how lilbee works with file:line citations

Opencode integration (coming)

Local-model opencode support is coming in #267, with tool-calling working across many GGUF families.

The demo shows a small local model (Qwen) given a specific instruction: when its first search comes back thin, widen lilbee's search settings and search again. The second pass returns the full function bodies with file:line citations. A more capable model would do the same from a higher-level prompt like "improve your search results." Read the lilbee-mcp skill to teach your own model the pattern.

agent fine-tunes lilbee mid-conversation: outline → widened retrieval → source with file:line citations

Agent integration

Drop the lilbee-mcp skill into .opencode/skills/ or .claude/skills/, register lilbee as an MCP server, and any MCP-aware coding agent can search your library, swap models, and tune retrieval. The skill is the single entry point: it documents every tool, the workflows the agent should follow, and points to drop-in AGENTS.md and worker-subagent starters under examples/agent-integration/.

The demos below use opencode with a cloud model. lilbee stays local; only the queries and the returned chunks go to the cloud model. Local-model opencode integration is on the way across many GGUF families: see Opencode integration (coming) above.

Live-indexing example: opencode (cloud model) indexes a Godot 4 pathfinding subset (~3s), then lilbee_search-es for AStarGrid2D and answers method-by-method against your local files.

an MCP-driven coding agent indexes a small local godot subset and answers with cited methods

It scales up. Pre-index Godot 4's full class reference (810 XMLs, 3449 chunks) and the same opencode + cloud setup writes a procedural level generator, every API call backed by a godot-classes/<Class>.xml:line citation; the side-by-side benchmark measured 4 hallucinated APIs without lilbee, 0 with.

cited codegen against the full Godot class reference

🇨🇳 中文文档镜像 AI 翻译 2026-06-27
英文原文章节由系统翻译为中文摘要，便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

lilbee 是一个开箱即用的本地数据与代码搜索引擎，旨在让你可以直接通过对话的方式与本地文档和代码库进行交互。它不仅是一个搜索工具，更是一个集成了检索与对话能力的智能助手，能够理解你的意图并基于本地上下文提供精准回答。

⚡ 功能介绍

lilbee 提供全方位的交互体验，支持 TUI、CLI、MCP server、REST API 以及 Python library，通过简单的 `pip install` 即可完成部署，无需额外配置守护进程、推理服务器或向量数据库。其核心亮点在于回答会精准引用源代码行，点击即可跳转；同时支持索引包括 PDF、Office 文档、电子书及 150 多种语言的源代码在内的各类文本数据。

📋 环境依赖

lilbee 采用 Standalone 模式，完全在本地运行，无需云端连接。硬件最低要求为 Apple Silicon Mac、2013 年以后的 64 位 Intel/AMD CPU 或 ARMv8 Linux 设备，配备 8 GB RAM 及 2 GB 磁盘空间。在 Linux 环境下，x86_64 版本需确保系统已安装 `libvulkan1`（如 Ubuntu 22.04+），否则在 Arch、Fedora 或 Alpine 等精简镜像中可能会因缺少 Vulkan loader 而导致 `lilbee self-check` 失败。

🛠 安装步骤（Docker/pip/源码）

安装方式分为两条路径：1. Python 环境安装：使用 `pip` 或 `uv` 安装（支持 Python 3.11 至 3.14），这种方式体积更小，且能根据机器硬件自动选择最优的 CPU 执行路径，适合已有 Python 环境的开发者。2. 独立捆绑包安装：提供 Standalone binary、Homebrew、AUR、Nix 或 Docker 构建版本，无需安装任何依赖，开箱即用。此外，如果你正在使用支持 MCP 的 Agent，可以直接通过 Agent 完成自动化配置。

🚀 使用教程

根据你的使用场景，lilbee 提供两种启动方式：如果你希望进行沉浸式交互，可以直接运行 `lilbee` 进入全屏终端应用（TUI），通过向导选择聊天与 Embedding 模型，并对文件进行索引；随后你可以在 TUI 中进行搜索与对话。TUI 内置了详尽的 Settings 界面，允许你精细调节搜索深度、距离阈值、Reranker 及分块（Chunking）策略，以适配不同规模的本地库。

⚙️ 配置说明（含 MCP / env）

对于通过 `pip` 或 `uv` 安装的用户，可以通过可选扩展进行增强，例如使用 `pip install --pre 'lilbee[crawler,litellm]'` 来添加爬虫或 LiteLLM 支持。而使用 Standalone binary 或 Docker 等构建版本时，所有功能已预装完毕。此外，若需通过 HTTP REST API（如 Obsidian 插件或自定义 GUI）调用 lilbee，建议通过 OS 启动器将其作为服务运行，以保持 HTTP server 处于热启动状态，避免冷启动延迟。

🔄 工作流/模块

lilbee 正在积极集成 Opencode 支持，未来将实现对多种 GGUF 格式本地模型的 Tool-calling 支持。通过集成 `lilbee-mcp` skill，你可以将 lilbee 注册为 MCP server 并放入 `.opencode/skills/` 或 `.claude/skills/` 目录中。这样，任何支持 MCP 的编程 Agent（如 Claude）都能直接调用 lilbee 进行库搜索、模型切换及检索参数调优，实现智能化的本地知识检索工作流。

🎯 aiskill88 AI 点评 B 级 2026-05-22

创新��MCP集成方案，结合本地搜索与AI对话。功能完整但生态成熟度有限，适合技术用户探索。

📚 实用指南（长尾问题）
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
  • 需要从图片、PDF 提取文字的文档自动化场景
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • 本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • 显存不足直接 OOM — 优先降低 context 或换更小的量化模型
  • Python 依赖冲突：建议用 venv / uv 隔离环境
部署方案
  • Docker：lilbee 提供官方镜像，docker compose up 一键启动
  • CLI：直接 npm install -g / pip install，命令行调用
  • 本地部署：CPU 8GB 起，GPU 推荐 16GB+ 显存
  • 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
lilbee 中文教程lilbee 安装报错怎么办lilbee MCP 配置lilbee Docker 部署lilbee Agent 工作流lilbee 与同类工具对比lilbee 最佳实践lilbee 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
  • 构建企业知识库 / RAG 检索应用的团队
  • 需要从图片、PDF 提取文字的文档自动化场景
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
  • 生产部署优先使用 Docker Compose 隔离依赖，并挂载 volume 持久化数据
  • 本地部署优先选 GGUF 量化模型，节省显存并保持响应速度
  • Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
  • MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
  • 容器内无法访问宿主机 localhost — 使用 host.docker.internal
  • 显存不足直接 OOM — 优先降低 context 或换更小的量化模型

👥 适合人群

Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师

🎯 使用场景

  • 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
  • 将多个 MCP 工具组合使用，构建个人专属 AI 工作站

⚖️ 优点与不足

✅ 优点
  • +标准化 MCP 协议，生态互联性强
  • +与 Claude 官方生态无缝对接
  • +即插即用，配置简单快捷
⚠️ 不足
  • −依赖 Claude 客户端，非 Claude 用户无法使用
  • −MCP 协议仍在持续演进，接口可能变更
  • −需要一定的配置步骤
⚠️ 使用须知

该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。

🔗 相关工具推荐

Context7代码文档平台
MCP工具
AI工程师中心
MCP工具
github-mcp-server MCP工具
GitHub官方MCP服务器实现，使AI助手能直接操作GitHub仓库、问题、拉取请求等资源。采用Go语言开发，高性能稳
mcp-use MCP工具
MCP工具
📚 相关教程推荐
MCP 配置教程
帮助中心 · AI Skill Hub
MCP 工具
帮助中心 · AI Skill Hub
Cursor AI 编程完全指南：Rules 配置、Composer 使用、MCP 集成
帮助中心 · AI Skill Hub
MCP 工作流生产级配置方案：从开发环境到团队共享
帮助中心 · AI Skill Hub
📰 相关 AI 新闻
OpenAI 最新产品与研究动态
AI 资讯 · 知识关联
AI Agent 自主化能力最新进展
AI 资讯 · 知识关联
多模态 AI 技术最新突破
AI 资讯 · 知识关联
Claude Code 最新功能与使用技巧
AI 资讯 · 知识关联
🍿 AI 圈相关吃瓜
配了5个 MCP 工具，Claude 一个都没用
AI 圈观察
AutoGPT 自主完成了任务：把我的文件夹全部重命名了
AI 圈观察
Filesystem MCP 帮 Claude 找文件，找了整个 node_modules
AI 圈观察
🗺️ 相关解决方案
mcp
mcp-server-setup
agent
ai-agent-workflow
workflow
ai-workflow-templates
ocr
document-ocr-pipeline
🧩 你可能还需要
基于当前 Skill 的能力图谱，自动补全的工具组合
技能寻求者
MCP · Agent · 工作流
Augustus
LLM安全测试框架，检测prompt注入、越狱等
natively-cluely-ai-assistant — Claude Skill 中文使用文档
免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。
DeepCode Agent工作流
MCP · Agent · 工作流
MemOS智能记忆系统
MCP · Agent · 工作流
CrewAI 多代理协作平台
MCP · Agent · 工作流

❓ 常见问题 FAQ

支持文本、代码、网页内容等多种格式，通过爬虫自动获取和索引。
💡 AI Skill Hub 点评

经综合评估，lilbee MCP工具 在MCP工具赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。

⬇️ 获取与下载
📚 深入学习 lilbee MCP工具
查看分步骤安装教程和完整使用指南，快速上手这款工具
⚙️ 安装教程 📚 使用教程
🌐 原始信息
原始名称 lilbee
原始描述 开源MCP工具：Terminal-first local search and AI chat over your documents, code, and crawled w。⭐18 · Python
Topics 本地搜索文档对话网页爬虫向量嵌入终端工具
GitHub https://github.com/tobocop2/lilbee
License NOASSERTION
语言 Python
🔗 原始来源
🐙 GitHub 仓库  https://github.com/tobocop2/lilbee 🌐 官方网站  https://lilbee.sh/

收录时间：2026-05-16 · 更新时间：2026-05-22 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →