team-reflect/reflect-open

Open-source Reflect rewrite: A local-first AI agent-friendly Markdown note-taking app

What it solves

Reflect provides a local-first, privacy-focused note-taking environment that keeps your data in standard Markdown files while offering modern features like semantic search, AI-assisted querying, and cross-device synchronization without locking your notes into a proprietary database.

How it works

The application operates on a local folder of Markdown files (a "graph"). It uses a Tauri-based architecture to provide a native desktop experience with features like wiki-style linking, backlinks, and local search. Users can optionally connect their own API keys (OpenAI, Anthropic, Google, or OpenRouter) to enable AI-powered querying of their notes, or configure transcription services for audio memos. The app includes a CLI for integration with external scripts and agents, and supports sync via iCloud or Git.

Who it’s for

It is for users who want a structured, connected note-taking system that prioritizes data ownership, privacy, and the ability to use their own AI models to interact with their personal knowledge base.

Highlights

  • Local-first architecture: Notes are stored as plain Markdown files, ensuring they remain accessible outside the app.
  • AI-powered insights: Query your notes using your own API keys from major LLM providers, with citations for all answers.
  • Privacy controls: Use private: true in notes to exclude specific content from AI processing or external services.
  • Extensible ecosystem: Includes a Chrome extension for web capture, a CLI for automation, and support for Git or iCloud-based synchronization.

Related

  • Project
    codexu/note-gen

    NoteGen is a local‑first Markdown note‑taking app that captures raw thoughts (text, voice, screenshots, links, etc.) and later uses LLMs to organise them into structured notes, with optional vector‑based knowledge‑base search, canvas diagrams, and extensible plugins.

  • Project
    mrsibe/KnowNote

    A local-first research workspace that turns documents into a knowledgeable base with traceable AI answers and local RAG processing.

  • Project
    kdsz001/OpenWiki

    A privacy-first desktop application that captures copied content and uses AI to automatically organize it into a structured, interconnected knowledge base and knowledge graph.