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 provides a polished, all-in-one SwiftUI workspace for local AI on Mac, integrating model discovery, advanced inference controls, and direct support for popular coding tools like Codex and Claude Code.
Who it is for
- Apple silicon Mac users wanting private, local AI
- Developers needing a local inference server with OpenAI/Anthropic compatibility
- AI enthusiasts who manage and experiment with MLX models
- Users of coding agents (Codex, Claude Code, etc.) seeking a local backend
Use cases
- Private chat and vision with local models, with persistent history
- Running a local API server compatible with OpenAI and Anthropic endpoints for other apps
- Discovering, downloading, and managing MLX models from Hugging Face
- Monitoring model performance with token usage, decode speed, and request analytics
Strengths
- Native SwiftUI experience with polished UI and menu bar controls
- Bundled mlx-vlm server with OpenAI/Anthropic API compatibility
- Performance dashboard tracking request volume, token metrics, and time to first token
- Integrations with coding tools (Codex, Claude Code, Pi, Hermes, OpenCode) for local inference
Considerations
- Requires macOS 26+ and Apple silicon, limiting compatibility
- First-time setup and model downloads need network access
- Dedicated audio-only and image-generation models are not yet supported (coming soon)
README quick start
Nativ
Local AI, native to your Mac.
Chat, serve, monitor, and connect MLX models from one macOS app.
Nativ is a native macOS workspace for running AI models locally on Apple silicon. It bundles an mlx-vlm server, finds compatible models in your Hugging Face cache (honoring HF_HUB_CACHE and HF_HOME), and wraps the whole experience in a polished SwiftUI app.
Use Nativ as a private chat app, a model manager, a performance dashboard, or an OpenAI- and Anthropic-compatible local inference server for the tools you already use.
What Nativ can do
| Feature | What you get |
|---|---|
| Local chat and vision | Streaming conversations, image attachments, reasoning output, response metrics, and persistent chat history. |
| Image generation and editing | Generate and edit images locally with compatible MLX image models in a dedicated Images tab. |
| Model library | Discover installed MLX models, browse and download compatible models from Hugging Face with fit warnings for your memory, inspect capabilities, switch models, or remove old ones. Preload separate language, image-generation, and speech models at once, with a warning if the combination would exceed your Mac's memory. |
| Performance analytics | Track request volume, token usage, time to first token, decode speed, model performance, and recent activity. |
| System monitor | Inspect live per-core CPU load, GPU utilization, unified memory and swap pressure, disk throughput, capacity, and SMART health. |
| Local APIs | OpenAI-compatible chat, Responses, image, audio, and model endpoints, plus Anthropic Messages endpoints. |
| Coding-tool integrations | Configure and launch terminal coding agents — Codex, Claude Code, Pi, Hermes, OpenCode, Aider, Goose, Crush, Qwen Code, OpenClaw — and set up editors — VS Code, Cursor, Zed, JetBrains, Cline, Continue — against models served by Nativ. See INTEGRATIONS.md for per-tool setup. |
| Developer workspace | Set the server host and port, add a Hugging Face token for gated models, inspect runtime details, copy endpoint URLs, search and filter live server logs, and monitor server health. |
| Menu bar controls | Start or stop the server, change the loaded model, check serving statistics, open the main app without breaking focus, or pin multiple live C |
Description
Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
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.
MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.