Why We Built Locke

AI-powered document chat tools are everywhere, but they all share the same problem: your data leaves your machine. Whether it's uploaded to a cloud API, stored on someone else's servers, or processed through a third-party pipeline, you lose control the moment you hit "upload."

We built Locke because we wanted a document chat tool that keeps everything local. No cloud APIs, no telemetry, no accounts, no data leaving your computer. Ever.

How It Works

Locke uses Retrieval-Augmented Generation (RAG) to ground AI responses in your actual documents:

Add folders containing your documents
Documents are parsed, chunked, and embedded locally using Ollama
Embeddings are stored in LanceDB on your machine
When you ask a question, the most relevant chunks are retrieved and sent to the LLM
The LLM generates an answer with clickable source citations

Click any source citation to preview the original file.

43 File Types

Locke supports PDFs, Word documents, spreadsheets, presentations, CSV files, HTML, images, and dozens more. With the optional vision model, you can even index screenshots, scanned documents, and photos.

Multiple AI Models

Choose from Llama 3.1, Mistral, Gemma, and any other model available through Ollama. Switch models any time from Settings.

4 Color Themes

Pick from Cyan, Violet, Rose, and Amber to make Locke your own.

Cross-Platform

Locke runs on Windows, macOS (Intel and Apple Silicon), and Linux. Same experience everywhere.

Get Started

Locke is available for $29.99 (one-time purchase, lifetime updates). Download the installer for your platform from the releases page. The setup wizard handles Ollama installation and model downloads automatically.