CarryOn – Cross-AI chat memory migration

One-click migration of chat history and memory across ChatGPT, Claude, and Gemini to avoid platform lock-in.

Problem

Users increasingly rely on chat AI as life and work assistants, but chat history and memory live only within one product. Switching to another subscription means losing all past context, making it costly to retrain the AI to understand them. Existing open-source solutions are either closed-source and paid, or outdated and require heavy fixes.

Solution

CarryOn is an open-source MCP server that aggregates chat history from ChatGPT, Claude, and Gemini, and exposes keyword search and context injection so any AI service can access cross-platform memory. Users deploy it to their own device (HAOS or Docker), then add the custom MCP server to their current AI service for seamless use.

Users

Knowledge workers, developers, and heavy users of multiple AI chat services.

MVP

Import chat export files from ChatGPT, Claude, Gemini; local vector index and keyword search; expose search and fetch endpoints via MCP server; one-click Docker deployment; privacy notes and data ownership options.

Revenue

Open-source core + hosted subscription ($5–10/mo) for one-click sync and cross-device access; enterprise tier for shared team memory and access control.

Why now

AI subscription competition is fierce, switching costs are high, and memory portability is a real pain. Existing open-source projects are under-maintained, so an indie developer can build a reliable, modern alternative solo.