Your conversations.
Ready to rediscover.
Turn scattered AI exports into a searchable, readable archive. Learn how to import, explore, continue, and listen — on your own server.
A guide for what comes next.
Build your first archive
Install, import a small export, and open your first search result.
Run a model locally
Set up a runtime, discover models, and start a conversation.
Give a response a voice
Enable speech and choose local or remote text-to-speech.
Use a headless server
Connect from a trusted LAN and configure the right permissions.
What do you remember?
Choose a starting point for your next archive search.
Hybrid search
Combine lexical matches and semantic similarity. Start here when you remember the subject and some of the language.
retry strategy for uploadsexample queryUse the web interface, archive HTTP API, or search CLI. Reader v1 and MCP keep their own semantic and keyword modes.
Read the search guideFollow the thread.
Know where your data goes.
Archive storage and search run locally. Model downloads and optional external AI, speech, or image requests have their own network boundaries.
Read the privacy guide