Give Claude Code memory of your meetings.
To give Claude Code memory of your meetings, connect a meeting-memory MCP server like Lookout. It reads the notetakers you already use, turns every transcript into a structured brain of decisions, commitments, people, and dates, and lets Claude Code answer questions about any past call — each answer traced to its source.
Last updated July 2026
Lookout is in private beta — join the waitlist for early access.
Why Claude Code forgets every call.
Claude Code is brilliant in the moment and amnesiac between sessions. It has no memory of last week's review, the pricing decision from a month ago, or who agreed to own the launch — so you end up re-pasting context by hand. The fix isn't a bigger model; it's a memory layer the model can reach.
Three steps to durable meeting memory.
Connect your notetakers
Point Lookout at the tools you already use — Fireflies, Granola, Otter. It reads across all of them; there's no rip-and-replace and no new notetaker to adopt.
Let it thread the memory
Every transcript becomes structured memory — decisions, commitments, people, dates — woven into one private graph that belongs to you, not the vendor.
Recall inside Claude Code
Connect Lookout as an MCP server. Now your Claude Code can answer questions about any past meeting, with every claim traced back to the moment it came from.
Giving Claude Code meeting memory.
Does Claude Code remember past meetings on its own?
No. Claude Code has no persistent memory of your meetings unless you connect one. Adding a memory layer over MCP — such as Lookout — gives it durable recall grounded in your actual transcripts.
What do I need to give Claude Code meeting memory?
A meeting-memory MCP server and the notetakers you already use. Lookout connects to Fireflies, Granola, and Otter, structures what they capture, and exposes it to Claude Code over the Model Context Protocol.
Is my meeting data private?
Yes. Lookout is built so the memory belongs to you, not the vendor — access is scoped and permissioned, and every answer is grounded in your own sources.
Do I have to switch notetakers?
No. Lookout is a layer on top of the notetakers you already run — you keep them and gain one memory across all of them.
When can I use Lookout?
Lookout is in private beta, launching to design-partner teams first. Join the waitlist at neurobaselabs.com/waitlist for early access.
Stop re-explaining your company.
Give your AI a memory.