AI-powered thought capture and recall — runs entirely on your machine.

Lore is a lightweight desktop app that sits in your system tray and lets you pop-up a hover chat with a button click to quickly capture thoughts. It uses a local LLM (via Ollama) and a local vector database (LanceDB) to store, understand, and retrieve your information — no cloud services, no API keys, complete privacy.

Think of it as your private second memory — a place to store anything you might need later. From long-form guides you’ve written for yourself, todo lists, decision summaries, urls, or even that exact curl you used to reproduce the bug in production. Everything stays organized and instantly searchable by simply describing it in plain language — even by date, or topic.

• Quick capture — press a global shortcut to pop up a chat bar, type a thought, and it's stored instantly
• Smart recall — ask questions in natural language and get answers sourced from your stored thoughts
• AI classification — input is automatically classified as a thought, question, command, or instruction
• Todo management — add, list, complete, and organize todos with priority and categories
• RAG pipeline — retrieval-augmented generation finds relevant context from your notes before answering
• Fully local — all data and AI processing stays on your machine

Download the latest release from the Releases page:

• Windows — Lore-x.x.x-Setup.exe
• macOS — Lore-x.x.x.dmg
• Linux — Lore-x.x.x.AppImage

You’ll be prompted to choose directories for your LLM models and for Ollama.

After installation, open the settings by clicking the Lore icon in the system tray → Settings. Navigate to Models, then download both an embedding model and an LLM. For best performance, follow Lore’s recommendations based on your system.

Press Ctrl+Shift+Space (or Cmd+Shift+Space on macOS) to toggle the Lore popup.

Just type naturally:

• "Daily note - sarah needs help with feature implementation"
• "The stripe webhook event that caused our refund bug {schawarma: true}"
• "add to my todo "talk to Daniel about the integration tomorrow"
• "todos: buy milk on the way home, and jump 12 times"

Lore classifies and stores your input automatically.

• "What notes did I write at daily today"
• "I'm about to go home, is there anything I need to do on the way home?"
• "what was the stripe webhook event that caused our bug?"
• "what's on my todo list?"

Lore searches your stored thoughts and generates an answer with relevant context.

• "My task about jumping 12 times is complete"
• "I purchased the milk you can remove it from the todos"
• "turns out daniel is on holiday, so change the todo we will meet him in the 4th"

• *"From now on, when I ask for my to do list, show the items in bullets, and add an emoji for each one."
• *"Always end a response by listing the original content & dates of the rows in the database which helped you give me this information."
• *"Start each conversation by calling me ."

• *What can you do?"
• *"Wassup my brotha Lore, tell me what u can do or I uninstall"

Right-click the tray icon and select Settings, or access settings to:

• Change the global keyboard shortcut
• Select chat and embedding models
• Pull or delete Ollama models
• Enable/disable start on login

Join the Lore Discord server to share feedback, ask questions, and connect with other users.

git clone https://github.com/ErezShahaf/lore.git
cd lore
npm install

npm run dev

MIT