asciimoo/hister
A personal search engine that indexes the full text of every page and file you've seen
Hister is a private search engine that indexes the full content of pages you visit and files you keep, so you can find them again later. You can search from a web interface, a terminal, or an AI assistant connected via MCP. Built in Go, it runs locally by default with no telemetry or mandatory cloud service.
What it does
- Indexes the actual content of visited pages and local files, not just titles or URLs
- Automatically saves newly visited pages through Firefox or Chrome browser extensions, and can also crawl sites or import existing browser history
- Searchable through a web UI, a terminal (TUI), the command line, or an AI assistant connected via MCP
- Supports advanced query features: field filters, phrase search, wildcards, negation, aliases, and result priorities
- No telemetry or cloud sync by default; optional semantic search sends document text to an embeddings endpoint you configure
Why it matters
It's aimed at people who want to search everything they've previously read or downloaded without relying on a third-party search engine or cloud service, keeping full control over their data. Its MCP support also connects that personal archive directly to AI assistants, fitting the growing trend of hooking personal knowledge bases into AI tools.
Terms in this repo
- MCP · A protocol that lets AI assistants connect to external tools and data sources
- Full text indexing · Storing entire document contents, not just titles, so they can be searched by their actual text
- Semantic search · A search method that finds documents with similar meaning even if the exact words don't match
- Embeddings · Numerical vector representations of text meaning, used to measure similarity
- Telemetry · Software automatically sending usage data to an external server
Repository description (English)
Your own search engine
Open on GitHubTrending repos
- DietrichGebert/ponytailA ruleset that teaches AI coding agents to say no to writing code
- liustack/modlensA plugin that lets text-only AI models like DeepSeek 'see' pasted images by turning them into structured text data
- marin-community/marinMarin is an open-source platform that publishes the entire process of building large language models, not just the final model
- TauricResearch/TradingAgentsA framework where multiple LLM agents split into analyst, researcher, trader and risk-management roles, debate, and decide stock trades
- Shubhamsaboo/awesome-llm-appsA free collection of 100+ ready-to-run AI agent and RAG app examples
- anthropics/claude-plugins-officialAnthropic's official catalog for add-ons that plug new abilities into Claude Code
- vorssaint/vorssaint-utilsOne free menu bar app replaces a dozen paid Mac utilities
- MadsLorentzen/ai-job-searchAn open-source framework that runs your entire job search through Claude Code, built by someone who actually got hired using it
Latest from METAL LAB
- Anthropic funds $5M research program for AI wellbeing evaluations
- Keenable Raises $26M Seed to Build Web Search for AI Agents
- Gamma acquires Accel-backed design startup Lica
- Oura's rumored September IPO is being priced on AI, not the ring
- Alabama Launches Investigation into OpenAI Agent Breakout Incident