Mnemoverse — Claude Code plugin: agent memory that learns
mnemoverse is a plugin for Claude Code and Codex that stores decisions and corrections in cloud memory via MCP. Agents recall them before acting, and memory syncs across tools.
MIT ★ 1,596 updated 2026-10-29
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install mnemoverse@awesome-codex-pluginsWhat mnemoverse does
The plugin bridges Claude Code to a remote Mnemoverse server over MCP: your agent saves important facts, decisions, and corrections, then recalls them before acting. Memory lives in your Mnemoverse account (OAuth sign-in, no API key), and one login works across Claude Code, Cursor, and VS Code.
Three commands come with it: /mnemoverse:remember stores facts, /mnemoverse:recall searches before work, /mnemoverse:memory-status shows counts. The plugin bundles the agent-memory-discipline skill (CC0), which teaches when to recall and what deserves saving—it works on any memory backend, not just Mnemoverse.
Sign-in is required: after install, run /mcp, select plugin:mnemoverse:mnemoverse and authenticate to Mnemoverse. The plugin records only what you or Claude explicitly save through the memory tools; it skips conversations, never touches chat history, and the skill refuses to persist secrets, API keys, or payment data.
What it helps with
- save a decision and retrieve it in a later session
- keep the same memory in Claude Code and Cursor
- surface contradictions in past decisions before you act
- maintain shared team memory in rooms
Example prompts for the agent
- Remember that we use pnpm instead of npm. We made this choice after a lockfile conflict.
- Before touching the billing module, recall what we decided about it in past work.
- /mnemoverse:memory-status after a week to see what your sessions have been saving.
How to install mnemoverse
Plugin marketplace
/plugin marketplace add hashgraph-online/awesome-codex-plugins/plugin install mnemoverse@awesome-codex-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about mnemoverse
How do I install mnemoverse in Claude Code?
Run two commands: /plugin marketplace add hashgraph-online/awesome-codex-plugins, then /plugin install mnemoverse@awesome-codex-plugins. Next, open /mcp, pick plugin:mnemoverse:mnemoverse and sign in via Mnemoverse.
What does mnemoverse store?
Only what you or Claude explicitly save through the memory commands: facts, decisions, corrections. Chat history is never recorded, and the skill refuses to save secrets or passwords.
What auth does mnemoverse use?
OAuth 2.1 with PKCE—no API key needed. You can revoke access anytime from the Mnemoverse console.
Source text
claude-plugin · MIT
# Mnemoverse Memory
[](https://hol.org/registry/plugins/mnemoverse%2Fmnemoverse)
Persistent memory for AI agents, shared across tools. One account gives Claude Code the same long-term memory it has in Cursor, VS Code, and any other MCP client: write a memory in one tool, recall it in another.
This plugin connects the hosted Mnemoverse memory server over MCP and adds the discipline that makes memory actually get used: recall before acting, save durable decisions and corrections afterwards.
## Install
One line, no directory and no review queue:
```
/plugin marketplace add mnemoverse/claude-plugin
/plugin install mnemoverse@mnemoverse
```
The first command registers this repository as a plugin marketplace; the second installs the plugin from it. Updates arrive with `/plugin marketplace update mnemoverse`.
To try it from a local checkout of this repository instead:
```
claude --plugin-dir ./
```
## Other hosts: OpenClaw and Hermes Agent
Both hosts install this repository as a plugin and load its skills, but neither starts a sign-in for a server that comes from a plugin. Add the hosted server once as the host's own entry, under the same name, and sign in there.
### OpenClaw
```sh
openclaw plugins install mnemoverse --marketplace https://github.com/mnemoverse/claude-plugin
openclaw plugins inspect mnemoverse
openclaw mcp add mnemoverse --transport streamable-http --url https://mcp.mnemoverse.com/mcp --auth oauth
openclaw mcp login mnemoverse
```
`mcp login` prints the sign-in URL instead of opening a browser, so open it yourself and approve the scopes; it waits on a loopback callback, which the Mnemoverse sign-in accepts on any port. `openclaw mcp probe mnemoverse` lists the tools once you are signed in. Full walkthrough: [Install by host, OpenClaw](https://mnemoverse.com/docs/api/install-by-host#openclaw).
### Hermes Agent
```sh
hermes plugins install mnemoverse/claude-plugin --no-enable
hermes plugins list
hermes plugins enable <name printed by hermes plugins list>
```
Then add the server to `~/.hermes/config.yaml`:
```yaml
mcp_servers:
mnemoverse:
url: "https://mcp.mnemoverse.com/mcp"
auth: oauth
```
and run `hermes mcp login mnemoverse` (Hermes opens the browser and waits on a loopback callback). Check with `hermes mcp test mnemoverse`. Keep the name `mnemoverse`: the native entry shadows the plugin's copy, which cannot sign in. Full walkthrough: [Install by host, Hermes Agent](https://mnemoverse.com/docs/api/install-by-host#hermes-agent).
## First run: sign in once, no API key
The server at `https://mcp.mnemoverse.com/mcp` uses OAuth 2.1 with PKCE. Installing the plugin does not open anything by itself: run `/mcp`, select the Mnemoverse server (from this plugin it is listed as `plugin:mnemoverse:mnemoverse`) and choose Authenticate, then sign in to your Mnemoverse account in the browser (free tier at [console.mnemoverse.com](https://console.mnemoverse.com?utm_source=github&utm_medium=readme&utm_campaign=claude-plugin), no credit card) and grant the requested scopes, which include `memory:read` and `memory:write`. There is no API key to paste, and access can be revoked at any time from the console. The bundled `setup` skill walks Claude through this if anything goes wrong.
## What you get
**Three commands:**
| Command | What it does |
| --- | --- |
| `/mnemoverse:remember` | save a durable fact, decision, or correction, one fact per memory |
| `/mnemoverse:recall` | search memory before acting, with provenance, surfacing contradictions instead of hiding them |
| `/mnemoverse:memory-status` | counts, domains, and the newest memories |
**Two skills:**
- `agent-memory-discipline` (CC0, backend-neutral): standing rules for when to recall and what is worth saving. It names no vendor and works on any memory backend; it ships here so the connected memory is actually used.
- `setup`: guides Claude through connecting and troubleshooting the MCP server.
**The tools come from the remote server itself**: reading and writing memories, a newest-first listing, stats, usefulness feedback, shared rooms (beta), and a vault alias listing (aliases only, values are never returned). The current list, with descriptions and schemas, is at the server's [card](https://mcp.mnemoverse.com/.well-known/mcp/server-card.json).
## Try these
1. `Remember that this project uses pnpm, not npm. We decided this after a lockfile conflict on 2026-08-01.`
2. `Before you touch the billing module, recall what we have decided about it in past sessions.`
3. `/mnemoverse:memory-status` after a week of use, to see what your sessions have been saving.
## What gets stored, and what does not
The plugin stores only what you or Claude explicitly save through the memory tools: single facts, decisions, corrections. It does not record conversations, does not read your chat history, and the bundled skill explicitly refuses to persist secrets, API keys, passwords, payment data, or personal identifiers.
Memory content lives in your Mnemoverse account. Privacy policy: [mnemoverse.com/docs/legal/privacy-policy](https://mnemoverse.com/docs/legal/privacy-policy).
## Troubleshooting
- **No sign-in prompt**: Claude Code does not open the browser by itself. Run `/mcp`, select `plugin:mnemoverse:mnemoverse` and choose Authenticate. If the server is not listed, add it for all your projects with `claude mcp add --transport http --scope user mnemoverse https://mcp.mnemoverse.com/mcp`; it then appears in `/mcp` as `mnemoverse`, and you authenticate it the same way.
- **`401` after it used to work**: the token expired; the next tool call normally refreshes it. If not, run `/mcp`, select the server and choose Re-authenticate.
- **`malformed_token` in logs**: something is sending an API key as a bearer token. The remote endpoint takes OAuth tokens only; API keys are for the [REST API](https://mnemoverse.com/docs/api/reference) and the local package.
More: [docs](https://mnemoverse.com/docs/api/remote-mcp-server).
## Why `.mcp.json` says `http` and `mcp.json` says `streamable-http`
Both files point at the same server, but each is read by a different host with its own vocabulary for the transport. `.mcp.json` is Claude Code's own project MCP config, where `type: "http"` is the canonical value ([code.claude.com/docs/en/mcp.md](https://code.claude.com/docs/en/mcp.md)); `streamable-http` is accepted there only as an alias. Root `mcp.json` follows the Agent Plugins 1.0.0 schema instead, whose `type` enum is `stdio | streamable-http | sse` and rejects `"http"` outright ([agent-plugins.org/schemas/1.0.0/mcp.schema.json](https://agent-plugins.org/schemas/1.0.0/mcp.schema.json)). `kimi.plugin.json` and the Cursor/Gemini manifests add two more dialects again (see `scripts/fixtures/`). `scripts/check-manifest-drift.mjs` guards all eight declarations of the server URL against drift while keeping each file's dialect intact; see its CI job, `manifest-drift-guard.yml`, for what it checks.
## Support
Issues in this repository, or [[email protected]](mailto:[email protected]).
The open-source MCP server package (MIT) lives at [mnemoverse/mcp-memory-server](https://github.com/mnemoverse/mcp-memory-server). A star there helps other builders find the project.
## License
Plugin: MIT. The bundled `agent-memory-discipline` skill is CC0-1.0 and lives at [mnemoverse/agent-memory-discipline](https://github.com/mnemoverse/agent-memory-discipline).
© Mnemoverse · MIT · hashgraph-online/awesome-codex-plugins