Sandbox
@asciimoo/hister

MCP search engine for browser history and files

Hister indexes the content of visited pages and local files so you can search them later. It exposes that index through a web app, a terminal interface, command-line tools, and an MCP server for AI assistants.

3,685 stars177 forksGoUpdated 6d ago
Who it's for

Builders who want their agent to search private notes, visited pages, and local files.

What it delivers

You can ask your agent to look up past pages and files instead of hunting through tabs and folders.

What it does

Full text search

Indexes page bodies and file contents, not just titles and URLs.

Browser capture

Uses Firefox and Chrome extensions to save newly visited pages.

MCP access

Lets an AI assistant query your personal index through an MCP server.

Terminal and web search

Provides a web interface, a TUI, and command-line search.

Semantic search

Can use an embeddings endpoint to find documents by meaning.

Importers and crawler

Can crawl websites and import existing browser history or data from supported services.

Multi-user separation

Keeps documents and search results separate for each user on a shared server.

How to get it

  1. 1On Linux or macOS, make it executable
    chmod +x hister
  2. 2Start Hister on Linux or macOS
    ./hister listen

README

Hister

Your own search engine

Hister is a private search engine for the pages you visit and the files you keep. It indexes their full contents so you can find information again from the web interface, terminal, or an AI assistant connected through MCP.

Try the demo · Download Hister · Read the quickstart · Documentation

Hister web interface

Quickstart

  1. Download the binary for your platform from the latest release, then rename it to hister (hister.exe on Windows).

  2. On Linux or macOS, make it executable:

    chmod +x hister
    
  3. Start Hister on Linux or macOS:

    ./hister listen
    

    On Windows, run .\hister.exe listen in PowerShell.

  4. Open http://127.0.0.1:4433 and install the browser extension for Firefox or Chrome.

No configuration is required for a local personal setup. See the complete quickstart to import existing browser history and choose what Hister indexes.

Features

  • Privacy focused: No telemetry or mandatory cloud service. Run Hister locally or on infrastructure you control.
  • Full text indexing: Search the actual contents of visited pages and local files, not only titles and URLs.
  • Automatic browser indexing: Save newly visited pages with the Firefox or Chrome extension.
  • Powerful queries: Use field filters, phrases, wildcards, negation, aliases, and result priorities.
  • Optional semantic search: Find documents by meaning through an embeddings endpoint you configure.
  • Crawler and browser import: Index websites or bring in existing browser history.
  • Web, terminal, and MCP clients: Search from the browser, TUI, command line, or an AI assistant.
  • Multi user support: Keep each user's documents and search results separate on a shared server.

Hister terminal interface

Privacy

By default, Hister has no telemetry and no cloud sync. The browser extension sends indexed page content only to the Hister server you configure, apart from downloading page favicons. The server stores documents and search indexes on that server.

Optional semantic search sends document text to the embeddings endpoint you choose. Review the privacy overview and semantic search configuration before enabling remote integrations.

Development

Requirements are Go 1.26, npm, and a C compiler for CGO dependencies.

git clone https://github.com/asciimoo/hister.git
cd hister
./manage.sh build

To work on the web app with hot reload and automatic Go rebuilds:

npm run serve:app

This starts a Vite development server and the Go backend with automatic rebuilds through air.

Community and contributing

Join us on IRCNet in #hister or on Discord.

Read CONTRIBUTING.md before submitting a change. Bugs and suggestions belong in the issue tracker. For security reports, see SECURITY.md.

Sponsors

Uruky

License

AGPLv3 or any later version

Files in the repo

Repository payload38 top-level entries
  • .forgejo
  • .github
  • client
  • cmd
  • config
  • contrib
  • files
  • nix
  • scripts
  • server
  • webui
  • .dockerignore
  • .editorconfig
  • .fallowrc.json
  • .gitattributes
  • .gitignore
  • .golangci.toml
  • .goreleaser-rolling.yml
  • .goreleaser.yml
  • .prettierignore
  • CHANGELOG.md
  • compose.yml
  • CONTRIBUTING.md
  • docker-bake.hcl
  • Dockerfile
  • flake.lock
  • flake.nix
  • generate.go
  • go.mod
  • go.sum
  • hister.go
  • LICENSE
  • manage.sh
  • package-lock.json
  • package.json
  • prettier.config.js
  • README.md
  • SECURITY.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More connectors

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

86k

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

43k

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

14k
okf-memory/
okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

547
tirth8205/
code-review-graph

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

31k
2akouwu/
reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

1.1k