M1K3

app.m1k3v1.0.0更新於 Oct 3, 2026

Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.

概覽

AI 產生的概覽

一款 Mac 應用程式,透過本機 MCP 端點向其他代理提供裝置端記憶、文件、語音與本機 AI 助理能力。

功能
M1K3 是一款 macOS 應用程式,在回送位址上透過 HTTP 執行自己的本機 MCP 伺服器。它提供以個人知識圖譜與 RAG 為基礎的知識檢索、文件存取、語音功能,以及用來詢問常駐裝置端 AI 的 ask_m1k3 工具。推論透過 MLX 在本機執行,並可選擇下載更大的模型。
適用情境
當你希望代理使用私密的裝置端知識庫、文件與本機模型,而非雲端服務時,它很有用。適合想把記憶與語音能力保留在自己電腦上的 Mac 使用者。
執行需求
Apple Silicon 上的 macOS 26 (Tahoe)、Xcode 26.x 與 Swift 6.2 工具鏈,以及 XcodeGen(可選 xcbeautify)。應用程式需從原始碼建置並使用個人開發團隊簽署。MCP 伺服器在本機回送 HTTP 位址上提供服務;模型需從 Hugging Face 下載一次,網頁搜尋預設為開啟。
安裝前請注意
在停用程式碼簽署的情況下建置,應用程式會脫離沙箱容器執行,並讀寫錯誤的資料位置。網頁搜尋預設為開啟,可在設定中關閉。可選的大型模型權重需從 Hugging Face 下載並佔用額外磁碟空間。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 M1K3,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

M1K3 for macOS — build from source

The flagship surface: a Mac-native SwiftUI app — on-device MLX inference, live voice (Kokoro TTS + WhisperKit STT), a personal knowledge graph with RAG, an embedded agent, a 3D companion, and a local MCP server other agents can call.

Private by design. M1K3 runs on your Mac. Models download once from Hugging Face; after that the only network use is web search, which is on by default so answers can be current, with one switch in Settings to turn it off. (An opt-in Apple Private Cloud Compute rung arrives in a later release; the 1.0 build has no cloud path.)

Requirements

  • macOS 26 (Tahoe) on Apple Silicon — hard requirement: the app uses Liquid Glass, on-device Foundation Models, and Metal via MLX.
  • Xcode 26.x (Swift 6.2 toolchain).
  • XcodeGen and (optional, nicer logs) xcbeautify: brew install xcodegen xcbeautify
  • Disk: nothing to download for the default brain (Mini runs on Apple's on-device models). Allow ~2–7 GB extra only if you opt into the bigger Lil/Big brains.

Build & run

bash
git clone https://github.com/Round-Tower/M1K3.gitcd m1k3/macos
# project.yml is the source of truth — M1K3.xcodeproj is generated, not trackedxcodegen generate
open M1K3.xcodeproj    # then ⌘R (set your own dev team for local signing)

Or from the command line:

bash
xcodebuild -scheme M1K3 -destination 'platform=macOS' build | xcbeautify# The same package graph also drives the iOS + visionOS shell (M1K3iOSApp/):xcodebuild -scheme M1K3iOS       -destination 'generic/platform=iOS Simulator'      build | xcbeautifyxcodebuild -scheme M1K3visionOS  -destination 'generic/platform=visionOS Simulator' build | xcbeautify

First launch is one screen: say hello (a name is optional) and you're talking — M1K3 starts on Mini, Apple's built-in on-device model, so there's nothing to download. Sharper local brains (Lil / Big) are one click away in Settings, or via the in-chat offer after your first answer; weights download only when you ask.

Signing note: run with your personal development team. Building with CODE_SIGNING_ALLOWED=NO compiles fine (CI does it) but the app then runs without its sandbox container and will read/write the wrong data locations.

Tests

The business logic lives in SwiftPM packages and tests without Xcode:

bash
swift test --parallel                 # the full fast suite (what CI runs)swift test --filter M1K3KnowledgeTests

Tests use swift-testing (import Testing, @Test), not XCTest.

Heavy MLX/Metal integration tests are env-gated off by default — M1K3_MLX_INTEGRATION=1 swift test opts in (downloads a real model and generates; Apple Silicon only).

Where things are

M1K3App/macOS app shell: SwiftUI views, AppEnvironment, settings
M1K3iOSApp/iOS + visionOS SwiftUI shell (M1K3iOS/M1K3visionOS schemes) on the shared Sources/ graph
Sources/SwiftPM modules: agent, inference, knowledge/RAG, voice, MCP
Tests/swift-testing suites per module
project.ymlXcodeGen spec (the .xcodeproj is a build artifact)
ROADMAP.mdWhat's next — kept current
PLAN.mdHistorical build log / decision record (append-only, signed)
docs/ADRs, model choices, MCP setup, release pipeline

MCP server

The running app serves MCP over HTTP at http://127.0.0.1:4242/mcp — knowledge search, documents, voice, and ask_m1k3 (ask the resident AI). See docs/MCP_SETUP.md to wire it into Claude Code or any MCP client.

Contributing

See CONTRIBUTING.md at the repo root. Found a bug? In the app: Settings → Report an issue… generates a redacted diagnostic you can attach to a GitHub issue.

來源:macos/README.md,提交 898ec88

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Oct 3, 2026