What is a Memory Bank?
A structured repository of information stored as markdown files, including `product-context.md`, `active-context.md`, `progress.md`, `decision-log.md`, and `system-patterns.md`.
@aakarsh-sasi
基本情報
MCP Server with Remote SSH support
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"memory-bank-mcp-aakarsh-sasi": {
"command": "npx",
"args": [
"@aakarsh-sasi/memory-bank-mcp"
]
}
}
}Initialize a Memory Bank in the specified directory
Set a custom path for the Memory Bank
Debug the current MCP configuration
Read a file from the Memory Bank
Write to a Memory Bank file
List Memory Bank files
Check Memory Bank status
Migrate Memory Bank files from camelCase to kebab-case naming convention
Track progress and update Memory Bank files
Update the active context file
Log a decision in the decision log
Switches to a specific mode
Gets information about the current mode
Processes the Update Memory Bank (UMB) command
Completes the Update Memory Bank (UMB) process
A Model Context Protocol (MCP) server that enables AI assistants to store and retrieve structured information across sessions using Memory Banks. It now supports storing Memory Banks on a remote server via SSH.
Install via npm (npm install @aakarsh-sasi/memory-bank-mcp) or run directly with npx (npx @aakarsh-sasi/memory-bank-mcp). Use command-line flags like --path, --folder, --mode, and --remote with --remote-user, --remote-host, --remote-path for remote mode. Configure as an MCP server in code editors like Cursor by specifying the npx command and arguments.
.clinerules filesA structured repository of information stored as markdown files, including `product-context.md`, `active-context.md`, `progress.md`, `decision-log.md`, and `system-patterns.md`.
Yes, use the `--folder` option to set a custom folder name (e.g., `--folder custom-memory`). The Memory Bank is created at `<project_path>/<folder_name>`.
Provide `--remote`, `--remote-user`, `--remote-host`, and `--remote-path` parameters. SSH key authentication is required; password authentication is not supported.
Modes: `code`, `architect`, `ask`, `debug`, `test`. Start with `--mode <mode>` or use the `switch_mode` tool during a session. Mode-specific `.clinerules` files can also trigger automatic switching.
You need SSH access to the remote server, SSH key authentication set up, and sufficient permissions to create/modify files in the specified directory.

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths
コメント