makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It combines privacy-first design (no data leaves the machine) with the ability to create a truly personalized writing assistant by training on your own messages and files, all powered by efficient QLoRA on Apple Silicon via MLX.
Who it is for
- Privacy-conscious writers who want AI assistance without cloud dependency
- Mac users (Apple Silicon) seeking a writing tool that mimics their personal voice
- Creative professionals who need to generate consistent brand or personal tone content
- Developers interested in local fine-tuning workflows for small language models
Use cases
- Drafting emails or messages in your natural voice from scratch
- Rewriting existing text to match your personal style
- Creating blog posts or journal entries that sound like you, not a generic AI
- Experimenting with personalized local LLMs for writing tasks
Strengths
- Complete privacy: ingestion, training, and generation never leave your Mac; no telemetry or accounts
- Uses user's own data (Mail, Messages, documents) to fine-tune a model that writes like them
- Leverages MLX and QLoRA for efficient training on Apple Silicon (M-series)
- Open source under PolyForm Noncommercial license, allowing verification and personal customization
Considerations
- Requires Apple Silicon Mac with at least 16GB RAM (32GB+ recommended for larger models) and macOS 14+
- Free for noncommercial use only; commercial use needs a separate license
- Effectiveness depends on having a sufficient and diverse corpus of your own writing
README quick start
Writekin
Writing that's kin to yours. Writekin ingests your own writing — Mail, Messages, documents, chat exports — curates it into a training corpus, fine-tunes a local language model (QLoRA on Apple Silicon via MLX), and then drafts and rewrites text that sounds like you. Everything happens on your Mac.
Screenshots
Overview — your corpus at a glance.
Compose — draft and rewrite in your voice.
Train — a local QLoRA run with a live loss chart.
Models — the on-device model library.
Privacy model
- Nothing leaves your machine. Ingestion, training, and generation are all local. There is no telemetry, no analytics, and no account.
- The auto-update check (Sparkle) requests one file — the release feed — and sends no system profile. That is the app's only network traffic besides model/tool downloads you explicitly start.
- Model weights download from Hugging Face on demand; the optional Messages-support tool downloads from its own official GitHub release, checksum-verified. Both happen only when you click.
- This repository exists so you don't have to take any of the above on faith: the source is the proof.
Requirements
- Apple Silicon Mac (M-series). 16 GB unified memory minimum; 32 GB+ recommended for training larger models.
- macOS 14 or newer.
- Full Disk Access (user-granted) if you want Mail and Messages ingested.
Install
Download the latest DMG from Releases, drag to Applications, open. The app guides you through source detection, Full Disk Access, and model download on first launch.
Messages support uses the open-source
imessage-exporter
(GPL-3.0), which Writekin downloads on demand — or use an existing
brew install imessage-exporter.
Build from source
brew install xcodegen
xcodegen generate
open Writekin.xcodeproj # build the Writekin scheme
The full test suite (xcodebuild test -scheme Writekin) must pass
before submitting changes — see CONTRIBUTING.md (note the contribution
licensing terms there).
New to the codebase? Start with ARCHITECTURE.md — the pipeline, the
folder map, and the invariants that keep it honest.
License
Writekin is source-available, free for personal (noncommercial) use under the [PolyFo
Description
Writing that's kin to yours
Related repositories
Similar projects matched by category, topics, and programming language.
uzairansaruzi
Featured
hermex
Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.
Blaizzy
Featured
nativ
Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.