EverMe plugin
Shared long-term memory for Claude Code, Codex, Cursor and nine more agents: CLI, MCP server and plugins for EverMe.
- 81 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Hooks send conversation fragments and facts to a cloud service, and agent tokens are stored in local files.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/evermeDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Hooks send conversation fragments and facts to a cloud service, and agent tokens are stored in local files.
This is third-party code. Review the repository files before installing.
What it does
The toolkit connects agents to the EverMe memory service. The `evercli` CLI signs in, installs plugins for chosen agents and checks the setup with `evercli doctor`. The MCP server exposes the `mem://profile` and `mem://search` resources, while hooks save facts and session summaries. Memory is shared per user rather than per project: Claude Code, Cursor, Codex and other agents read and write one pool, so context moves between apps and devices. For Claude Code the plugin brings hooks, the `/recall` and `/everme-help` commands, a skill describing the memory tools and MCP.
Who it is for. People who work with several agents on different machines and want them to remember preferences, decisions and project history.
Good fit when
- A decision made yesterday in Claude Code is needed today in Cursor on another laptop.
- An agent should recall the profile and agreements for a project at the start of a session.
- The `/recall` command pulls facts from past conversations on request.
- One memory pool is connected to Claude Code, Codex and OpenCode at once.
Not a fit when
- Conversation content must not leave for an external cloud.
- You want memory only inside a single repository with no account.
- A notes file in the project root is enough.
Example request
Recall what I decided about the database layout last week and continue from there.Limitations
The repository holds only the client side. The EverMe app, accounts and storage server are separate and need an account on their service, or your own EverOS and its address in `EVERME_API_BASE`. Sign-in goes through the browser, and agent tokens sit in files with `0600` permissions. Kimi Code asks you to run `/plugins install ~/.kimi-code/everme` inside the agent after setup, and WorkBuddy asks you to trust the MCP server. Memory is global per user: facts from one project can surface in another, which matters on a machine with a shared account.
How to disable. Run `evercli plugin uninstall <agent>` for each connected agent and remove the CLI with `npm uninstall -g @everme/cli`. Saved memories live in the service and are deleted there.
FAQ
How do I connect EverMe to Claude Code?
Install the CLI with `npm install -g @everme/cli`, sign in with `evercli auth login` and run `evercli plugin install claude-code`. Then run `evercli doctor`.
Which agents are supported?
Claude Code, Claude Desktop, Codex, Cursor, Devin, DeepSeek Harness, Hermes, Kimi Code, OpenCode, OpenClaw, Raven and WorkBuddy. Each has an `evercli plugin install` command.
Can memory stay on my own server?
Yes. Deploy the EverOS engine and set `EVERME_API_BASE` to its address before `evercli auth login`, and the CLI will use your endpoint.
How does the agent recall the past?
Through the `mem://profile` and `mem://search` MCP resources, and in Claude Code also through `/recall`. Simply ask what it remembers about you.
Where are agent tokens stored?
In files with `0600` permissions, for example `~/.claude/everme.env` for Claude Code. The CLI redacts secrets such as `evt_*` and `emk_*` in its output.
Discussion
No questions or reviews yet.
Related
PluginsA long-term memory plugin that keeps decisions, preferences and task state across sessions and injects only what a query needs
Long-term memory for agents: a remote MCP server, plugins for Claude Code, Cursor and Codex, and an API for your own apps
Shared local memory for AI agents: Claude Code, Codex, Cursor and others find the agreements of past sessions in it and record new ones
Long-term memory for Claude Code, Cursor and Codex: the agent saves decisions and finds them again in later sessions
Agent memory as a graph of linked facts: decisions and errors outlive the session, with no vector database or paid API calls
Persistent memory for coding agents: insights are stored as markdown cards and recalled at the start of the next session.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| EverMe (this card) | yes | OAuth | 81 | |
| claude-supermemory | yes | 2,803 | keeps memory for one agent; EverMe shares one pool across twelve agents | |
| Claude-Mem | no | 116,457 | compresses Claude Code sessions locally; EverMe syncs memory across agents and devices through a service |
README in short
The repository explains how to connect agents to EverMe memory: CLI install, sign-in, plugins and verification. It also describes the MCP and hooks flow, building the Go CLI and Node plugins, and the output contract with token redaction.