The Letta connector for Muse

Give your agents a memory that persists.

The Letta connector manages long-term memory for AI agents: list agents, read their core-memory blocks, manage archival passages, and message agents to record new context. It’s the difference between an agent that forgets and one that accumulates.

Use it to inspect what an agent actually remembers, correct stale facts, or seed new knowledge — all in plain language.

What Muse can do with Letta

List agents and inspect their memory state
Read and update core-memory blocks
Search and manage archival memory passages
Message agents to record new context

Try asking

“What does the support agent remember about our refund policy?”
“Add our new pricing to the sales agent’s memory.”
“Search the agent’s archival memory for onboarding notes.”

Safety notes

Memory edits confirm first — a wrong memory corrupts future behavior.
Each agent’s memory is scoped; Muse only touches the agent you name.
This is a community-built connector. Review its permissions before connecting.

How to connect Letta

Open the Muse app, go to settings, and find connectors. Link your Letta account with the standard sign-in — Muse never sees your password. Once linked, the connector is available across your conversations. You can scope it to read-only or disconnect it entirely at any time from the same screen.

Questions

What’s the difference between core memory and archival memory?

Core memory is the always-loaded blocks (persona, key facts). Archival is the larger searchable store. Muse can work with both.

Can Muse delete things an agent remembers?

Yes, with confirmation, useful for removing outdated facts before they cause bad answers.

Related connectors

Connector status last checked October 13, 2026. The authoritative, current list lives in the Muse app's settings, under connectors. Back to the full directory →