OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Personal AI Memory

Personal AI Memory is a local-first Chrome extension that captures conversations from ChatGPT, Gemini, Claude, Grok and Perplexity, stores them in a browser-based memory graph, and uses hybrid search to retrieve context for later chats.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Personal AI Memory — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when earlier conversations contain context you want to retrieve and reuse while chatting on one of its five supported AI services.

Who it is for

  • People who use multiple supported AI chat services and want one searchable archive of their conversations.
  • Developers who want to build or modify an open-source browser extension for local conversation retrieval.

Documented uses

  • Search past conversations using semantic similarity and keyword matching.
  • Bring relevant conversation memories into a new chat through the Recall control.
  • Export or import a JSON backup of stored memories, including embeddings.
Before you choose

Requirements & limits

The README describes a Chrome Web Store installation and a manual release installation. It states that no account or API key is required and that the extension uses no server. The project is open source under Apache-2.0.

  • It supports ChatGPT, Gemini, Claude, Grok and Perplexity.
  • Memory is stored locally using IndexedDB; embeddings run in the browser, and keyword indexing uses BM25.
  • The Recall feature inserts retrieved context into supported chat inputs rather than providing a separate hosted assistant.
  • A JSON export and import option supports backup and transfer of the stored memory.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the extension from a release ZIP

Manually load a downloaded release into Chrome.

Before you start

  • A release ZIP from the project's Releases page
  • Chrome

Steps

  1. Download the latest ZIP from the Releases page.

  2. Unzip the downloaded file.

  3. Open chrome://extensions/ and turn on Developer mode.

  4. Choose Load unpacked and select the unzipped folder.

Expected outcome

The extension is loaded in Chrome from the release folder.

Guide limitations

  • The Chrome Web Store version may lag behind the latest release.
Documentation 1 ↗
Source-based practical guide

Build and load a development version

Build the extension from source and load its development output in a supported browser.

Before you start

  • Node.js 18 or later
  • pnpm
  • Chrome or Edge with Manifest V3 support

Steps

  1. Clone the repository and change into its directory.

  2. Run pnpm install.

  3. Run pnpm dev to build in development mode.

  4. In chrome://extensions/, use Load unpacked to load build/chrome-mv3-dev/.

Expected outcome

The development build is loaded as an unpacked browser extension; the development command auto-rebuilds on saves.

Guide limitations

  • After code changes, reload the extension and refresh open AI-service tabs.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
marswangyang/personal-ai-memory · Official homepage title · retained in its source language
How we review sourcesSuggest a correction