Eclaire
Search your documents, organize notes and schedule tasks with a self-hosted AI assistant that connects to local text and vision models.
Eclaire is a self-hosted AI assistant for notes, documents, photos, bookmarks and tasks. You can ask questions about saved material, inspect the sources behind an answer and ask the assistant to create notes or update tasks. Scheduled automations handle recurring requests such as a weekly task summary.
Models and data storage run locally by default. Eclaire connects to llama.cpp, Ollama, LM Studio, vLLM and MLX through OpenAI-compatible APIs. Text and vision models handle conversation and document processing. External providers process requests if you choose to connect them.
The web interface accepts PDFs, Office documents, Markdown and other file formats. It extracts document content and image text, organizes assets with tags and saves readable or PDF versions of bookmarks. A REST API supports custom integrations.
Docker Compose provides the documented setup on macOS, Linux and Windows. An installable PWA, Telegram, Apple Shortcuts and Android automation tools provide other ways to reach the same instance. These mobile connections use your self-hosted backend.
Eclaire uses the MIT license and is in pre-release development. Its maintainers advise against exposing it directly to the public internet; use a private network or an authenticated proxy for remote access.
