Hister

Hister is a private search engine that indexes visited web pages and local files for full content search.

Hister is a private, self-hosted search engine that turns visited web pages and local files into a full-content search index. It collects data through browser extensions, local file watching, history imports, and website crawlers, extracting and indexing content on a server you control. Users can search the index using fields, phrases, wildcards, negation, and date ranges, and view clean previews alongside results. The software features no telemetry, no mandatory cloud, and optional semantic search with configurable embeddings endpoints. It provides multiple interfaces including a web interface, terminal client, HTTP API, CLI, and MCP server, supporting single binary local runs, Docker, Nix, SQLite, and PostgreSQL.

Hister at a glance

Best for: Software engineer, Researcher
Runs on: Web, CLI, API, Chrome extension, self-hosted
Pricing: Free software AGPLv3
Released: January 2026
Category: AI search engine
Website: hister.org

Key features

Browser extensions for automatic page indexing
Local file watching and website crawling
Full text search with field filters and wildcards
Stored readable previews alongside search results
Multiple interfaces including web, terminal, and API
Self-hosted deployment with SQLite or PostgreSQL
Optional semantic search with embeddings
Skip, priority, and version tracking rules

Use it for

Search across previously visited web pages and local files
Find exact information using advanced query operators
Retrieve stored content through an AI assistant via MCP
Monitor and index local folders automatically

Alternatives to Hister

DeepSearcher — Performs evaluation and reasoning based on private enterprise data using various models.
Exa — Provides high-accuracy web search and deep research endpoints for AI agents.
Firecrawl — Provides direct web data access for AI agents with open source flexibility.
XERJ — It answers agent questions from an index instead of wasting tokens on context windows.
Orama — Runs in browsers, servers, and edge networks with zero dependencies.
PixelRAG — Preserves visual structure like tables and charts that text parsers miss.
Brave Search — It uses an independent index and protects user privacy.
DeepSearch — Your API key stays in your browser and searches never touch external servers.
Jina — It provides reliable reader and search APIs optimized for LLMs and RAG systems.
Searchbase — Independent web access with support for REST, MCP, self-hosting, and managed cloud.
Scira — Provides minimalistic AI search with citations.
AnySearch MCP — It delivers high accuracy, fast latency, and structured outputs for AI agents.

All Hister alternatives