memory_plugin MCP server
Commit Oct 21, 2026Provides local-first long-term memory and hybrid RAG to help AI coding agents retain context, preferences, and project knowledge across sessions.
Also known as Lotargo/memory_plugin, memory-plugin, @lotargo/memory_plugin
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 21, 2026
- License
- MIT
What is memory_plugin MCP?
memory_plugin provides local-first long-term memory and hybrid RAG to help AI coding agents retain context, preferences, and project knowledge across sessions.
Summary generated from the project's README
About memory_plugin MCP server
Helping AI coding agents retain project context and personal preferences across different sessions is the primary function of memory_plugin. It provides a local-first solution for developers using MCP clients like Claude Code, Codex, Gemini CLI, OpenCode, or Antigravity. By using Git-based identity, the server ensures that memory remains consistent within specific projects while keeping unrelated work isolated.
Users can manage their knowledge through a local web UI to browse Notebook records, edit instructions, and review knowledge graphs. The system utilizes hybrid full-text and vector retrieval to search through Markdown files, PDFs, spreadsheets, and code. Everything runs locally using CPU inference and SQLite indexes, meaning no external vector database or hosted embedding API is required. While storage is local, users have the option to create manual ZIP cloud checkpoints via Turso for backups.
What you can do with it
- 1Persist architectural decisionsAsk your coding agent to save specific technology stack details so they are remembered in future sessions.
- 2Retrieve long-form documentationSearch through ingested PDFs, spreadsheets, or web pages using hybrid retrieval to find project details.
- 3Manage memory via visual interfaceUse a local web panel to browse records, edit instructions, and view knowledge graphs.
Written from the project's README. Every use case is checked against a quote from it.
How to install memory_plugin MCP
Formats verified 10 Nov 2026Install memory_plugin MCP in Claude Code
$ claude mcp add memory-plugin -- npx -y @lotargo/memory_pluginInstall memory_plugin MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Install memory_plugin MCP in VS Code
.vscode/mcp.json
{
"servers": {
"memory-plugin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Install memory_plugin MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Install memory_plugin MCP in Codex
~/.codex/config.toml
[mcp_servers.memory-plugin] command = "npx" args = ["-y", "@lotargo/memory_plugin"]
Install memory_plugin MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablelotargo/memory_plugin is public and reachablegithub.com/lotargo/memory_plugin ↗Pass
- Package names this repository as its source@lotargo/memory_plugin names lotargo/memory_plugin as sourcenpmjs.com/package/@lotargo/memory_plugin ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-21github.com/lotargo/memory_plugin ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @lotargo/memory_pluginPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub@lotargo/memory_plugin
Local-first long-term memory, hybrid RAG, and agent personalization for AI coding agents.
Quick Start · Web UI · First use · Documentation
Why use it?
AI coding assistants lose preferences, architectural decisions and investigation context between sessions. memory_plugin keeps that knowledge available across OpenCode, Codex, Claude Code, Gemini CLI, Antigravity and other MCP clients.
- Keep useful context across sessions. Save concise facts and working instructions in human-readable Markdown, with tags, history and explicit persona controls.
- Retrieve the details when needed. Search long-form Notes, PDF, DOCX, spreadsheets, web pages and code with hybrid full-text/vector retrieval, source links and a knowledge graph.
- Follow the project across checkouts. Git-based identity keeps project memory consistent while isolating unrelated projects and global context.
- Manage memory in one local panel. Browse and edit records, instructions and sources, configure models, and review backup and maintenance actions.
- Run locally. CPU inference and local storage need no Docker, external vector database or hosted embedding API. Full ZIP cloud checkpoints through Turso are optional; there is no telemetry.
Quick Start
Requirements
- Node.js 22.16+ in the 22.x branch, or 24+ (
^22.16.0 || >=24.0.0); Node 23 is excluded. - npm/npx and a supported coding client or another MCP-capable client.
CPU execution is the stable default. WebGPU is experimental.
Install
Choose the client you want to configure. For Codex:
npx -y @lotargo/memory_plugin setup --codex
Other client flags: --opencode, --claude, --gemini, --antigravity.
Setup installs the selected integration and bundled skill, and adds managed memory instructions where supported. Existing unrelated configuration is preserved.
To set up OpenCode, Codex, Claude Code, Gemini CLI and Antigravity together, omit the client flag:
npx -y @lotargo/memory_plugin setup
Restart the configured client or open a new session to load the integration. For Codex, check the connection with:
npx -y @lotargo/memory_plugin doctor --codex
See installation and client integration for marketplace installation, client configuration locations, headless setup and removal.
Local Web UI
Open the shared local panel:
npx -y @lotargo/memory_plugin web
Browse and edit Notebook records, active instructions, history, project scopes and knowledge sources. The panel also provides source links and graphs, settings, model controls, and reviewed backup and maintenance actions.
The screenshot uses fictional demo records. The panel supports English (default), Russian and Simplified Chinese, with a saved language choice, plus light, dark and system themes. It listens on 127.0.0.1 and opens with a private connection URL. Saved-memory browsing needs no cloud account or embedding model.
See the web UI guide for editing, lifecycle, authentication, ports and autostart.
First use
In a Git project, ask your connected agent to save a fact:
Remember for this project: the API uses Fastify and Zod.
After the agent confirms it has saved the fact, open a new session in the same project and ask:
What API stack have we saved for this project?
The agent reads the saved Notebook context with recall(scope: "project"). You can also inspect the saved record in the web panel. Global memory is available outside Git projects; pass directory when explicitly targeting a workspace.
The agent can call remember with:
{
"fact": "The project API uses Fastify and Zod.",
"title": "API Stack",
"kind": "fact",
"scope": "project"
}
OpenCode initializes memory automatically. For other supported clients, restart the client or open a new session after setup to load the managed startup instructions. See installation and client integration for client-specific behavior and troubleshooting.
For an instruction the agent should actively apply, use kind: "directive". Save a long investigation with remember_note, and external source material with ingest_document. Notes and sources are searched on demand instead of being injected into every session.
See memory architecture and personalization for routing, source links and client behavior.
Storage, Privacy, and Security
Working memory stays local: Markdown Notebook files, SQLite indexes and archived source text. Optional cloud-snapshots mode stores full ZIP checkpoints in Turso; it does not perform live synchronization. Snapshot upload is manual by default and can be scheduled explicitly.
- Agent scope
allmeans global + current project, keeping unrelated project memory isolated. - No telemetry or analytics are sent.
- Model weights download from Hugging Face on first use and are cached locally.
- URL ingestion and configured cloud operations use the network.
- Cloud credentials are encrypted locally and machine-bound; this is not an OS keychain.
- Removing client integrations preserves memory unless a data purge is explicitly requested.
Older hybrid-sync / only-cloud installations require the documented migration flow. See storage, cloud snapshots and security before migrating or restoring data.
Documentation
The documentation index contains the full guides and release records.
| Guide | What you will find |
|---|---|
| Installation and clients | Setup flags, verification, headless setup, uninstall and recovery |
| Memory architecture | Facts, Notes, sources, Git scopes, hybrid retrieval and graph |
| Personalization | Directives, native persona, client prompts and migrations |
| Web UI | Notebook/projects, knowledge editing, graphs, models and panel lifecycle |
| Maintenance and recovery | Migrations, RAG import/export/reset, diagnostics and file cleanup |
| Storage and cloud snapshots | Checkpoints, scheduling, legacy recovery, authentication and security |
| MCP / CLI / configuration | Tool and command reference, defaults, model controls and troubleshooting |
| Development and tests | Local repository linking, test commands and evaluation |
| Benchmarks | Included corpora, methodology, results and limitations |
| Local marketplaces | Codex / Claude Code channels and migration |
Repository benchmarks describe the included datasets and configurations; they do not establish general benchmark superiority.
License
memory_plugin MCP questions
How do I add memory_plugin MCP to Claude Code?
Run claude mcp add memory-plugin -- npx -y @lotargo/memory_plugin in your terminal. Add --scope user to make it available in every project.
How do I add memory_plugin MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does this plugin require an external vector database?
No, it runs entirely locally without the need for Docker, an external vector database, or a hosted embedding API.
How can I manage and view my saved memory records?
You can use a local web panel to browse and edit Notebook records, instructions, history, and knowledge sources.
Is my data sent to a cloud provider?
Working memory stays local; however, you can optionally use cloud snapshots via Turso for manual or scheduled backups.
Which AI coding clients are supported?
It supports OpenCode, Codex, Claude Code, Gemini CLI, and Antigravity.