hister

Hister is a personal search engine designed to index web pages and files you choose to keep. It can be accessed through a web interface, terminal, or AI assistant via MCP. To set up Hister locally, download the binary for your platform, rename it to hister (hister.exe on Windows), and run .\hister.exe listen in PowerShell. Ensure the server is running to enable indexing and searching of pages and files.

The browser extension for Firefox or Chrome must be installed to start indexing web pages. After enabling the extension on a web page, return to Hister and search for a phrase from that page to find the first indexed result. No configuration is needed for a local personal setup. For more advanced indexing options, users can import browser history, index local directories, or import files. Alternative installation methods include using Homebrew, Docker, or Nix, as detailed in the installation guide.

Hister does not collect telemetry or cloud sync data by default. The browser extension only sends indexed page content to the configured Hister server, excluding downloading page favicons. The server stores documents and search indexes on the server itself. Optional semantic search sends document text to an embeddings endpoint of your choice, but this feature should be reviewed in the privacy overview and semantic search configuration before enabling remote integrations.

Unlike conventional search engines, Hister creates a personal search index from the web pages and files you select. Your content remains on your Hister server, making it ideal for locating information you've previously accessed without depending on a third-party search provider. To develop Hister, ensure you have Go 1.26, npm, and a C compiler for CGO dependencies.

For web app development with hot reload and automatic rebuilds, start a Vite development server and the Go backend, following the instructions in CONTRIBUTING.md. Report bugs and suggestions in the issue tracker, and address security concerns in SECURITY.md.