M1K3
app.m1k3v1.0.0更新于 Oct 3, 2026
Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.
概览
一款 Mac 应用,通过本地 MCP 端点向其他智能体提供设备端记忆、文档、语音和本地 AI 助手能力。
- 功能
- M1K3 是一款 macOS 应用,在回环地址上通过 HTTP 运行自己的本地 MCP 服务器。它提供基于个人知识图谱与 RAG 的知识检索、文档访问、语音功能,以及用于询问常驻设备端 AI 的 ask_m1k3 工具。推理通过 MLX 在本地运行,并可选择下载更大的模型。
- 适用场景
- 当你希望智能体使用私密的设备端知识库、文档和本地模型而非云服务时,它很有用。适合希望把记忆和语音能力保留在本机的 Mac 用户。
- 运行要求
- Apple Silicon 上的 macOS 26 (Tahoe)、Xcode 26.x 与 Swift 6.2 工具链,以及 XcodeGen(可选 xcbeautify)。应用需从源码构建并使用个人开发团队签名。MCP 服务器在本地回环 HTTP 地址上提供服务;模型需从 Hugging Face 下载一次,网页搜索默认开启。
安装
在 SourceWeft 中
- 打开 控制台中的 M1K3,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
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
Or from the command line:
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=NOcompiles 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:
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
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.
来源:macos/README.md,提交 898ec88
工具
0版本历史
1- v1.0.0最新Oct 3, 2026
