M1K3 MCP server

M1K3 — Own your AI

Local AI that runs entirely on your Apple-Silicon Mac — on-device LLM inference, live voice, a personal knowledge graph with RAG, encrypted call transcription, a local agent, and an MCP server. Private by design: on your Mac by default, no telemetry, and every network call shows itself and can be switched off.

⬇ Download for macOS · m1k3.app · TestFlight beta

Connecting a coding agent → m1k3.app/agents

Requires macOS 26 Tahoe or later · Apple Silicon · signed & notarized (Developer ID).

What's inside

answers, Qwen 3 4B, and Gemma 4 12B via MLX. Chat with Mini from the first second while a bigger brain downloads.

• On-device inference — three brains: Apple Foundation Models for instant

a full-window voice mode with karaoke captions.

• Live voice — sentence-streamed neural TTS + on-device speech-to-text, and

when you correct something, the dream cycle supersedes the stale fact instead of silently losing either version, and keeps the history visible.

• Knowledge + RAG — drop in notes and PDFs; M1K3 remembers and cites, locally.
• A memory that repairs itself — a temporal memory graph of dated facts;

low-poly 3D companions rendered on-device with RealityKit.

• A face, and creatures — the pixel face by default; an opt-in cast of

markdown + syntax-highlighted code in chat.

• Call memory — encrypted, on-device call transcription.
• A local agent — tools that do things, grounded in your own data, with

resident with a voice, a memory, and your knowledge.

• MCP server — 18 tools over local HTTP; give Claude and other agents a

Everything above runs on the device. M1K3 uses the network for two things: the one-time download of a bigger brain when you ask for one, and web search, which is on by default so answers can be current, with one switch in Settings to turn it off. The 1.0 build has no cloud path at all. A later release adds an opt-in Private Cloud Compute rung — off by default, one message at a time, every PCC answer labelled — see SECURITY.md.

Shortened. The full README is on GitHub.