Skip to main content
Membase gets smarter the more context it has. There are three ways to bring your context in: import past conversations, let your agents capture context as you work, and connect external apps.

​
Chat History Import

The fastest way to bootstrap your knowledge base. If you’ve been using ChatGPT, Claude, or Gemini, you already have months of context in those tools. Chat History Import brings it all into Membase at once.
Chat History Import
1

Export from your LLM client

Download your conversation history using each platform’s export feature (ChatGPT Settings > Data controls > Export data, etc.).
2

Upload to Membase

Go to the Sources page in your dashboard, scroll to the Chat History section, and upload the exported file. Membase accepts the native export formats from each platform.
3

Membase digests your history

Your conversations are processed through the same pipeline as live interactions. Preferences, decisions, project context, and relationships are extracted and added to your knowledge graph.
You don’t have to choose between import and live sync. Import your history first to bootstrap, and then let your agents continue building your knowledge base as you work.

​
Live Agent Conversations

Once you’ve connected an agent via the Quickstart, context is captured automatically as you chat. Your agent calls add_memory whenever it detects something worth remembering: preferences, decisions, project details, and more.
Live agent sync via MCP: Add Memory being called during an agent conversation
You don’t need to do anything special. Just chat normally, and your knowledge base grows in the background.

​
App Integrations

Your context doesn’t only live in AI conversations. Connect external apps from the Sources page to bring in context from the tools you use every day.

Gmail

Project updates, team discussions, and action items from your inbox.

Google Calendar

Meetings, deadlines, and schedule context.

Slack

Messages, threads, and channel discussions from your workspace.
Connected integrations
Once connected, data syncs automatically. Incremental updates run in the background, so your memory stays current without any manual effort.
For the full list of supported and upcoming integrations, see the Apps guide.

​
What Gets Captured

SourceExamples of extracted context
Chat History ImportPast preferences, project decisions, technical stacks, recurring patterns across months of conversations
Agent ConversationsNew preferences, decisions made during the session, project details discussed in real time
GmailProject updates, action items, team communication, client context
Google CalendarMeeting outcomes, deadlines, scheduling patterns, recurring events
SlackTeam discussions, channel updates, thread summaries, shared decisions
All sources feed into the same knowledge graph. Context from an imported ChatGPT conversation connects to context from a Slack thread if they reference the same project, person, or decision.

​
Next Steps

Use Your Context

Learn how to retrieve and interact with your stored knowledge.

How Membase Works

Understand the full digesting and retrieval pipeline.