memory_plugin MCP server
Commit 21 Okt 2026Menyediakan long-term memory berbasis local-first dan hybrid RAG untuk membantu AI coding agent mempertahankan konteks, preferensi, dan pengetahuan proyek di berbagai sesi.
Juga dikenal sebagai Lotargo/memory_plugin, memory-plugin, @lotargo/memory_plugin
- Stars
- 2
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- —
- Commit terakhir
- 21 Okt 2026
- Lisensi
- MIT
Apa itu memory_plugin MCP?
memory_plugin adalah MCP server. Menyediakan long-term memory berbasis local-first dan hybrid RAG untuk membantu AI coding agent mempertahankan konteks, preferensi, dan pengetahuan proyek di berbagai sesi.
Ringkasan dibuat dari README proyek
Tentang memory_plugin MCP server
Fungsi utama dari memory_plugin adalah membantu AI coding agent mempertahankan konteks proyek dan preferensi pribadi di berbagai sesi yang berbeda. Plugin ini menyediakan solusi local-first bagi developer yang menggunakan MCP client seperti Claude Code, Codex, Gemini CLI, OpenCode, atau Antigravity. Dengan menggunakan Git-based identity, server ini memastikan memori tetap konsisten di dalam proyek tertentu sambil menjaga agar pekerjaan yang tidak terkait tetap terisolasi.
User dapat mengelola pengetahuan mereka melalui web UI lokal untuk menelusuri catatan Notebook, mengedit instruksi, dan meninjau knowledge graph. Sistem ini menggunakan hybrid full-text dan vector retrieval untuk mencari melalui file Markdown, PDF, spreadsheet, dan kode. Semuanya berjalan secara lokal menggunakan CPU inference dan index SQLite, yang berarti tidak memerlukan vector database eksternal atau hosted embedding API. Meskipun penyimpanan bersifat lokal, user memiliki opsi untuk membuat checkpoint cloud ZIP secara manual melalui Turso untuk keperluan backup.
Apa yang bisa Anda lakukan dengannya
- 1Mempertahankan keputusan arsitekturMinta coding agent Anda untuk menyimpan detail teknologi stack tertentu agar dapat diingat pada sesi mendatang.
- 2Mengambil dokumentasi format panjangCari melalui PDF, spreadsheet, atau halaman web yang telah di-ingest menggunakan hybrid retrieval untuk menemukan detail proyek.
- 3Mengelola memori melalui antarmuka visualGunakan web panel lokal untuk menelusuri catatan, mengedit instruksi, dan melihat knowledge graph.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal memory_plugin MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal memory_plugin MCP di Claude Code
$ claude mcp add memory-plugin -- npx -y @lotargo/memory_pluginInstal memory_plugin MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Instal memory_plugin MCP di VS Code
.vscode/mcp.json
{
"servers": {
"memory-plugin": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Instal memory_plugin MCP di VS Code CLI
$ code --add-mcp '{"name":"memory-plugin","type":"stdio","command":"npx","args":["-y","@lotargo/memory_plugin"]}'Instal memory_plugin MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Instal memory_plugin MCP di Codex
$ codex mcp add memory-plugin -- npx -y @lotargo/memory_pluginInstal memory_plugin MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.memory-plugin] command = "npx" args = ["-y", "@lotargo/memory_plugin"]
Instal memory_plugin MCP di Gemini CLI
$ gemini mcp add -s user memory-plugin npx -- -y @lotargo/memory_pluginInstal memory_plugin MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"memory-plugin": {
"command": "npx",
"args": [
"-y",
"@lotargo/memory_plugin"
]
}
}
}Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaulotargo/memory_plugin is public and reachablegithub.com/lotargo/memory_plugin ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernya@lotargo/memory_plugin names lotargo/memory_plugin as sourcenpmjs.com/package/@lotargo/memory_plugin ↗Lolos
- Provenance build (atestasi Sigstore)No build attestation published for this releaseTidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-10-21github.com/lotargo/memory_plugin ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from @lotargo/memory_pluginLolos
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di 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
Pertanyaan tentang memory_plugin MCP
Bagaimana cara menambahkan memory_plugin MCP ke Claude Code?
Jalankan claude mcp add memory-plugin -- npx -y @lotargo/memory_plugin di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan memory_plugin MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Apakah plugin ini memerlukan vector database eksternal?
Tidak, plugin ini berjalan sepenuhnya secara lokal tanpa memerlukan Docker, vector database eksternal, atau hosted embedding API.
Bagaimana cara saya mengelola dan melihat catatan memori yang tersimpan?
Anda dapat menggunakan web panel lokal untuk menelusuri dan mengedit catatan Notebook, instruksi, history, dan sumber pengetahuan.
Apakah data saya dikirim ke penyedia cloud?
Working memory tetap berada di lokal; namun, Anda dapat secara opsional menggunakan cloud snapshots melalui Turso untuk backup manual atau terjadwal.
Client AI coding mana saja yang didukung?
Plugin ini mendukung OpenCode, Codex, Claude Code, Gemini CLI, dan Antigravity.