Hister is an open-source (AGPLv3), self-hosted personal search engine that turns visited web pages, local files, browser history, and crawled websites into a private, full-text search index under your control.

The main features and capabilities of Hister include:

• Multi-Source Data Ingestion: Collects and indexes content automatically via browser extensions (Chrome and Firefox) as you visit pages, file system watchers on local folders, browser history imports, or site crawlers.

• Full-Content Extraction & Previews: Indexes the full text of documents—moving beyond basic filenames or titles—and stores clean, readable content previews alongside search results.

• Precision Querying & Index Rules: Supports field filters, quoted phrases, wildcards, negation, date ranges, and custom query aliases, alongside priority ranking, skip rules, sensitive content checks, and content versioning.

• Multi-Interface & MCP Integration: Accessible through a web interface, terminal client, HTTP API, CLI, and a Model Context Protocol (MCP) server for direct AI assistant retrieval.

• Privacy & Flexible Deployment: Operates with zero telemetry or mandatory cloud connections on a single local machine or a multi-user server using SQLite or PostgreSQL. Deployment is supported via single binaries, Docker, or Nix, with optional semantic search through custom embedding endpoints.