/memfree

MemFree - Hybrid AI Search Engine

Primary LanguageTypeScriptMIT LicenseMIT

MemFree

MemFree – Hybrid AI Search Engine

An Open Source Hybrid AI Search Engine


Introduction

MemFree is a Hybrid AI search engine that simultaneously performs searches on your personal knowledge base (such as bookmarks, notes, documents, etc.) and the Internet.

Highlights

  • Hybrid AI Search Engine: Combines Knowledge Base and Internet Search
  • One-Click Chrome Bookmarks Sync and Indexing
  • Support Image-Based Search
  • Integrates Multiple Search Engines as Sources
  • Support multiple AI Models
  • Self-Hosted, Super-Fast Serverless Vector Database
  • Full Code Open Source
  • One-Click Deployment

MemFree Hybrid AI Search Workflow

MemFree Hybrid AI Search workflow

ChangeLog

MemFree ChangeLog

Tech Stack

Hybrid AI Search Full Tech Stack

One-Click Deployment

MemFree One-Click Deployment guide

1 Deploy Backend with Zeabur

Deploy on Zeabur

2 Deploy Frontend with Vercel

Deploy with Vercel

3 One Command Deploy Backend with Fly.io

Self-Hosted Installation

Prerequisites

Intsall Bun

curl -fsSL https://bun.sh/install | bash

Upstash Redis

Create a Redis compatible database in seconds: Upstash Redis

OpenAI API Key

Get an OpenAI API Key: OpenAI

Searxng Search

Deploy on Zeabur

You could one click get the Searxng Search Service.

Frontend

cd frontend

bun i

cp env.example .env

bun run dev

Vector Service

cd vector

bun i

bun run index.ts

Extension

cd extension

bun i

bun run build

Set MemFree as your search engine

Set MemFree as your search engine

Contributing

Here's how you can contribute:

  • Open an issue if you believe you've encountered a bug.
  • Make a pull request to add new features/make quality-of-life improvements/fix bugs.

Help and Support

Roadmap

License

MemFree is backed by MemFree and licensed under MIT.

Credits

  • bun – Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
  • lancedb – Developer-friendly, serverless vector database for AI applications
  • fastembed-rs – Library for generating vector embeddings, reranking in Rust
  • next-saas-stripe-starter – Open-source SaaS Starter with User Roles & Admin Panel.
  • next-chrome-starter – Next.js Chrome Extension Starter
  • ai-chatbot – A full-featured, hackable Next.js AI chatbot built by Vercel