Skip to main content
Chat in Dashboard (also known as “Chat with Memory”) lets you talk to your Membase knowledge base directly from the dashboard, without having to open an external agent. Ask about a decision you made last month, a conversation from last week, or a pattern across everything you’ve worked on, and the answer is grounded in your own memories and wiki documents.
Chat with Memory interface

​
What Chat Pulls From

Every answer is built from your two knowledge stores:
  • Memory: Personal context captured through your agents and integrations (preferences, decisions, meetings, emails, and so on).
  • Wiki: Factual knowledge you or your agents stored as wiki documents.
Chat uses search_memory and search_wiki as tools under the hood. The underlying model decides which tools to call based on your question and weaves the results into a single grounded answer. You can also ask Chat to save new wiki documents during the conversation (for example, “save this as a wiki doc titled X”); Chat will then call add_wiki with the content.

​
Highlights

  • Context-grounded responses: Every answer draws from your actual memories and wiki, not general world knowledge
  • Citations: Each response links back to the exact memories and wiki documents it drew from, so you can verify and explore further
  • Graph panel: See how referenced memories and documents connect to each other
  • Session history: Past conversations are saved in the sidebar so you can pick up where you left off
  • Write back to Wiki: Ask Chat to save a summary, decision, or reference as a new wiki document and it will create one for you
  • Model picker: Switch between Standard and Advanced models from the model dropdown in the composer
Advanced models cost 2x usage per message compared to Standard models. You will see a (2x) suffix next to Advanced model names in the picker.
Chat in Dashboard is useful for exploring your own knowledge base, verifying what your agents know about you, and quickly looking up past decisions or reference material without switching to an external agent.

​
When to Use Chat vs an Agent

You want to…Use
Recall a decision, preference, or past conversationChat in Dashboard
Look up factual knowledge you stored in the wikiChat in Dashboard
Verify what an agent knows about youChat in Dashboard
Save a decision or summary as a new wiki documentChat in Dashboard
Do real work (code, draft, plan) with memory-aware helpConnected agent (Cursor, Claude, ChatGPT, etc.)
Save a new memory during flowConnected agent

​
Next Steps

Memory

Explore and manage the memories behind each Chat answer.

Knowledge Wiki

Explore and manage the wiki documents behind each Chat answer.

Membase MCP

See how Chat uses search_memory and search_wiki under the hood.

Connect Agents

Use Membase through external agents like Cursor or Claude.