product update

Gemini now imports chats and memory from ChatGPT, Claude, and other AI apps

TL;DR

Google is rolling out chat and memory import functionality to Gemini, allowing users to transfer conversation history from ChatGPT, Claude, and other AI apps. The feature supports zip file uploads up to 5 GB, with users able to upload up to 5 files per day. A companion memory import tool lets users generate context summaries from other chatbots to paste into Gemini.

2 min read
0

Google is rolling out the ability to import chats and memory context into Gemini from competing AI assistants, including ChatGPT and Claude.

The import feature is accessed via a new "Import memory to Gemini" option in Settings & help, directing users to gemini.google.com/import. The tool offers two distinct import paths.

Chat Import

Import chats allows users to export conversation data from other AI platforms and upload the resulting .zip file directly to Gemini. Google explicitly supports ChatGPT and Claude exports, with users able to upload up to 5 zip files per day, each up to 5 GB in size.

For ChatGPT, the export process involves navigating to Settings > Data controls > Export data. Claude users follow: Settings > Privacy > Export data, then select their desired date range. Both platforms send download links to the user's registered email address.

Imported conversations appear in Gemini's side panel marked with a distinct import icon. Users can search, delete individual conversations, or remove entire imports. Reuploading a zip file adds new conversations and overwrites previously imported ones.

Memory Import

A second method, Import memory, works differently. Users input a specific prompt into their current AI assistant requesting it summarize what it knows about them across all past conversations. The prompt instructs the AI to structure output into five categories: Demographics, Interests & Preferences, Relationships, Dated Events/Projects/Plans, and Instructions/Rules.

The prompt explicitly requires the summarizing AI to avoid first and second-person pronouns, instead referring to "the user" in third person, and to preserve user statements verbatim where possible. Users then copy the resulting summary and paste it into Gemini.

Availability and Restrictions

The import feature is not available in the EEA, Switzerland, or the United Kingdom—regions where Google faces stricter data portability and privacy regulations.

The rollout accompanies the release of Gemini 3.1 Flash Live, though the import tool functions with any version of Gemini.

What this means

Google is directly addressing a friction point for users switching to Gemini: the loss of chat history and learned context. By supporting both structured chat export and memory summarization, Google removes a significant barrier to adoption. The 5 GB upload limit and 5-files-per-day constraint suggest Google is managing server load while supporting realistic migration scenarios. The geographic restrictions indicate compliance with European data regulations that may impose additional obligations around imported personal data. For ChatGPT and Claude users with extensive conversation histories, this feature materially reduces the switching cost—though the quality of imported memory depends on how well competing models can summarize their learned context about individual users.

Related Articles

product update

Google embeds Gemini across Android as multimodal agent before Apple's WWDC AI reveal

Google is rolling out Gemini-powered features across Android that enable the AI to understand screen context and complete multi-step tasks across apps, marking a shift from traditional assistant interactions to agentic capabilities. The updates will launch on Samsung Galaxy and Google Pixel phones this summer before expanding to watches, cars, and laptops.

product update

Google launches Gemini Intelligence for Android, enabling multi-app task automation

Google announced Gemini Intelligence at I/O 2026, a system-level AI layer that automates multi-step tasks across Android apps. Rolling out first to Samsung Galaxy and Pixel phones this summer, it enables the OS to understand screen context and execute complex workflows without manual app-switching.

product update

Google announces Googlebooks laptop platform with Gemini AI integration, launching fall 2026

Google previewed Googlebooks, a new laptop platform combining Android and ChromeOS with Gemini AI at its core. The platform features AI capabilities like Magic Pointer for contextual assistance and seamless Android phone integration. Hardware partners include Acer, Asus, Dell, HP, and Lenovo, with devices launching fall 2026.

product update

Notion launches Developer Platform with custom code execution, agent orchestration, and database sync

Notion has launched a Developer Platform that allows teams to run custom code in cloud-based Workers, sync external databases, and orchestrate both internal and external AI agents. The platform, free through August, supports integration with Claude Code, Cursor, Codex, and Decagon, and uses Model Context Protocol for agent connectivity.

Comments

Loading...