Practical overview
When it fits
Use Lore when you want to build a local store of personal notes and tasks that you can query later, rather than relying on memory or searching separate files.
Who it is for
- People who want a searchable personal store for notes, guides, decisions, URLs and technical details.
- Desktop users who want to manage todos through natural-language input.
- People who prefer local model processing and storage for this personal knowledge workflow.
Documented uses
- Capture a thought or work detail from a system-tray popup.
- Find earlier information by asking a question in plain language, including by topic or date.
- Add, list, complete or revise todo items through natural-language instructions.
- Set recurring preferences for how Lore formats or contextualizes replies.
Requirements & limits
The README lists desktop installers for Windows (.exe), macOS (.dmg) and Linux (.AppImage). The public repository is licensed under MIT.
- Setup requires choosing locations for Ollama and model files and downloading both an embedding model and an LLM.
- Lore’s documented recall searches information stored in the app and generates answers with relevant context.
- Knowledge exploration, MCP support, semantic reasoning and multi-device sync are listed as roadmap items rather than current documented features.
- The project is a TypeScript desktop application; its README also documents development setup with npm.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up Lore and its local models
Install Lore and select the local models it needs for capture and recall.
Before you start
- A Windows, macOS or Linux desktop.
- The Lore installer from the project’s GitHub Releases page.
Steps
Install Lore and choose directories for the LLM models and Ollama when prompted.
Open Settings from the Lore system-tray icon and go to Models.
Download both an embedding model and an LLM, following Lore’s system-based recommendations.
Use Ctrl+Shift+Space on Windows or Linux, or Cmd+Shift+Space on macOS, to open Lore’s popup.
Expected outcome
Lore is installed with both model types selected and its capture popup accessible by keyboard shortcut.
Guide limitations
- This setup guidance does not specify particular model names or hardware requirements.
- The project lists installer formats for these desktop platforms; the guide does not establish compatibility for particular systems.
Capture and retrieve personal information
Save a note or task in Lore and ask a natural-language question about stored information.
Before you start
- Lore installed with an embedding model and an LLM selected in Settings.
Steps
Open the Lore popup with the configured global shortcut.
Type a thought or task in natural language, such as a note about a decision or a request to add an item to the todo list.
Later, ask a question about the saved information or request a todo list.
Expected outcome
Lore classifies and stores the input, then searches stored thoughts and generates an answer with relevant context when asked.
Guide limitations
- Answers draw on information captured in Lore; the README describes retrieval from stored thoughts.
- Lore’s broader personal-agent direction is described as early.
Compare options for Vector search
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Lore | Capture a thought or work detail from a system-tray popup. | Desktop, Self-hosted | The README lists desktop installers for Windows (.exe), macOS (.dmg) and Linux (.AppImage). The public repository is licensed under MIT. |
| Remind | Capture digital activity for later recall. | Desktop, macOS, Self-hosted | The repository describes a first version for macOS and provides source setup instructions. It lists an Apache-2.0 license. |
| Aml Multiagent Rag | Ingest PDF regulations, extract and chunk their text, and build a searchable vector collection. | Docker, Self-hosted | The repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 12 October 2026
- Original website title
- ErezShahaf/Lore · Official homepage title · retained in its source language