zouwei/moraya

An extremely elegant open-source Markdown/Typst AI Agent, Bridging AI capabilities and user sovereignty.

What it solves

Moraya is a lightweight, privacy-focused AI agent and editor designed for users who want a seamless writing experience combining Markdown and Typst without sacrificing data sovereignty. It eliminates the need for heavy, cloud-dependent editors by providing a native, ultra-lightweight application that integrates local and cloud AI directly on the user's device.

How it works

Built with Rust and Tauri v2, Moraya acts as a local hub for content creation. It uses a ProseMirror-powered WYSIWYG editor for Markdown and a dedicated source-plus-preview environment for Typst. The application integrates AI via a "Bring Your Own Key" (BYOK) model, where API keys are stored in the OS Keychain and requests are proxied through a Rust backend to ensure security. It further extends AI capabilities through the Model Context Protocol (MCP), allowing the AI to call local tools and access a managed knowledge base.

Who it’s for

It is designed for writers, students, and researchers who require high-quality typesetting (via Typst), privacy-first AI assistance, and a fast, minimal memory footprint.

Highlights

  • Dual-Format Editing: Instant WYSIWYG for Markdown and native compiled previews for Typst.
  • Deep AI Integration: Support for 11+ chat providers (including Ollama for local LLMs), 71+ AI templates, and multimodal vision input.
  • MCP Ecosystem: A dynamic container for Model Context Protocol servers with a one-click marketplace for autonomous AI workflows.
  • Voice-to-Text: Real-time speech transcription with speaker diarization and AI-generated meeting summaries.
  • Privacy-First Architecture: Local-only storage, OS Keychain for API keys, and no intermediary servers between the user and AI providers.
  • Ultra-Lightweight: A native app with a ~10MB installer and tiny memory footprint.

Related

  • Project
    HKUDS/nanobot

    An ultra-lightweight, self-hosted personal AI agent framework that combines long-term memory, MCP integrations, and scheduled automation across WebUI, terminal, and various chat apps.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    ailia-ai/ailia-models

    A collection of 419 pre-trained AI models across various domains like vision, audio, and text, all runnable via a unified CLI with automatic weight downloads.

  • Project
    Kieirra/murmure

    Murmure is an open‑source desktop app that provides offline, privacy‑first speech‑to‑text using NVIDIA’s Parakeet TDT 0.6B v3 model. It runs locally on Windows, macOS, and Linux, supports 25 European languages, and offers a simple push‑to‑talk UI with no telemetry.

  • Project
    dograh-hq/dograh

    Dograh AI is an open‑source, self‑hostable platform for building and testing voice conversational agents. It provides a visual workflow editor, telephony integrations (Twilio, Vonage, etc.), and a modular LLM/STT/TTS stack that you can replace with any provider. One‑command Docker setup gets the whole system running locally, and Python/Node SDKs let you create agents programmatically. The project is BSD‑2 licensed and backed by a Slack community.