M1K3

app.m1k3v1.0.0Updated Oct 3, 2026

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

VerifiedSTDIODesktop onlyAI & MLFiles & StorageKnowledge & Memory

Overview

AI-generated overview

A Mac app that exposes on-device memory, documents, voice, and a local AI assistant to other agents over a local MCP endpoint.

What it does
M1K3 is a macOS app that runs its own local MCP server over HTTP on the loopback interface. It offers knowledge search over a personal knowledge graph with RAG, document access, voice features, and an ask_m1k3 tool that queries the resident on-device AI. Inference runs locally via MLX, with optional larger model downloads.
When to use it
Useful when you want an assistant to draw on a private, on-device knowledge base, documents, and a local model rather than a cloud service. Suited to Mac users who want memory and voice capabilities kept on their own machine.
Requirements
macOS 26 (Tahoe) on Apple Silicon, Xcode 26.x with the Swift 6.2 toolchain, and XcodeGen (plus optional xcbeautify). The app is built from source and signed with a personal development team. The MCP server is served locally at a loopback HTTP address; models download once from Hugging Face, and web search is on by default.
Before you install
Building with code signing disabled makes the app run without its sandbox container and read or write the wrong data locations. Web search is enabled by default and can be turned off in Settings. Optional larger model weights download from Hugging Face and use extra disk space.

Installation

In SourceWeft

  1. Open M1K3 in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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.

Source: macos/README.md at commit 898ec88

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 3, 2026