Letta Agent Memory Connector for Muse
Give agents persistent memory with Letta (ex-MemGPT) — memory blocks, archival recall, and a usable free tier.
- What
- Give agents persistent memory with Letta (ex-MemGPT) — memory blocks, archival recall, and a usable free tier.
- Cost
- Free
- Needs
- A Letta API key (Letta account — free tier at $0 with bring-your-own API keys; paid plans from $20/month for heavier use), kept in your Muse's secure vault (never paste secrets here). Memory is long-lived: memory writes are confirmed by default and never happen silently.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
A Muse agent skill that works with Letta, the stateful-agent platform born from Berkeley's MemGPT research: create agents with persistent memory blocks, read and write memory, archive and recall conversation history, and manage agent state across sessions. Memory writes are confirmed by default — memory is long-lived and hard to audit later, so nothing gets written silently. Letta offers a usable free tier ($0 with bring-your-own API keys; the core server is also open-source and self-hostable), with paid plans from $20/month for heavier use. Uses a Letta API key, kept in Muse's secure vault. Draft: written from Letta's public docs, not yet live-tested end-to-end — Skill Harbor never reviews the code, review it yourself before use. No secrets in the repo.
Curated by Skill Harbor — free, open-source build (MIT) by @bluman1.
Version:
Install
Prerequisites: A Letta API key (Letta account — free tier at $0 with bring-your-own API keys; paid plans from $20/month for heavier use), kept in your Muse's secure vault (never paste secrets here). Memory is long-lived: memory writes are confirmed by default and never happen silently. No GitHub account needed unless listed here. Install "Letta Agent Memory Connector for Muse" for me. A Muse agent skill that gives agents persistent memory with Letta — memory blocks, archival recall, agent state — writes always confirmed. Repository: https://github.com/bluman1/muse-connectors/tree/main/connectors/letta 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "letta". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my Letta API key in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.