Skip to main content
Glama

๐Ÿง  Personal Memory Gateway (PMG)

The Privacy-First Memory Layer for AI.
Seamlessly bridge your local knowledge with any AI assistant through a secure, MCP-compatible gateway.

NPM Version License Built for MCP


๐Ÿš€ Quick Start

Get up and running in seconds with zero configuration:

npx @shubham-01-star/pmg init

Related MCP server: M3 Memory

โœจ Overview

Personal Memory Gateway (PMG) is a local-first backend designed to store, manage, and serve your personal knowledge to AI models. It acts as a secure "VPN for your memory," ensuring that sensitive data is redacted and privacy is gated before any context is shared.

๐Ÿ› ๏ธ Core Capabilities

  • MCP Tool Integration: Seamlessly connects to Cursor, Claude Desktop, and other MCP clients via query_personal_memory and save_memory tools.

  • Privacy-First Ingestion: Automatically watches local directories, chunks documents, and stores them in a local vector database (LanceDB).

  • Intelligent Redaction: Applies a multi-stage pipeline to redact PII and sensitive information before retrieval.

  • Archestra Integration: Optionally route responses through high-performance gateways like Archestra (supporting Gemini/OpenAI).

  • Telemetry Dashboard: Monitor system health and manage your indexed data through a built-in web interface.


๐Ÿ—๏ธ Architecture

graph TD
    A[Local Files] -->|Ingestion| B(Chunking & Embedding)
    B -->|LanceDB| C[Vector Repository]
    D[MCP Client] -->|Query| E[Privacy Pipeline]
    E -->|Redaction| F[Consent Gate]
    F -->|Context| G[AI Model]
    C -->|Retrieval| E

๐Ÿ“ฆ Installation

npm i -g @shubham-01-star/pmg
pmg init
pmg

Local Development

git clone https://github.com/shubham-01-star/pmg.git
cd pmg
npm install
npm run build
npm run run

๐Ÿ”Œ MCP Client Configuration

Add PMG to your mcpServers configuration:

{
  "mcpServers": {
    "pmg": {
      "command": "npx",
      "args": ["-y", "@shubham-01-star/pmg"],
      "env": {
        "INGEST_DIR": "/path/to/your/data",
        "LANCE_DB_PATH": "/path/to/lancedb/storage"
      }
    }
  }
}

โš™๏ธ Environment Variables

Variable

Description

Default

INGEST_DIR

Directory to watch for memory files

my_data

ARCHESTRA_ENABLE

Enable Archestra integration (0 or 1)

0

EMBEDDING_PROVIDER

Embedding model source (local, gemini, etc.)

local

DASHBOARD_PORT

Port for the telemetry dashboard

8787

PRIVACY_REDACT_PII

Enable PII redaction pipeline

1


๐Ÿ“Š Dashboard

Once running, access the telemetry dashboard at: ๐Ÿ‘‰ http://localhost:8787/dashboard

  • Monitor: Real-time events and memory retrieval stats.

  • Manage: Upload new documents or clear existing memories.

  • Status: Visual health probes for all internal services.


๐Ÿงช Testing & Verification

PMG includes a comprehensive suite of smoke tests and backend validations.

# Run backend smoke suite
make test-backend

# Integrated flow test
node scripts/one-command-flow.mjs "topic" "path/to/sample.txt"

๐Ÿ“œ License

Distributed under the MIT License. See LICENSE for more information.


Available Tools

2 tools
query_personal_memoryA

Search local memory and return privacy-filtered personal context for a topic. MUST call this tool when user asks to query memory, asks personal preference/history, or explicitly says 'call tool query_personal_memory'. Do not skip tool call in those cases.

Inputs: topic (required).

save_memoryA

Save a new fact, preference, or piece of information to the user's permanent memory. MUST call this tool when user says 'remember this', 'save this', or explicitly says 'call tool save_memory'. Do not reply with a normal answer before attempting the tool call.

Inputs: fact (required), category.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A4.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one for querying memory and one for saving memory. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    Both tool names follow the verb_noun pattern with underscores, using 'query' and 'save' as verbs and 'memory' as the object, which is consistent and predictable.

    Tool Count3/5

    With only two tools, the set feels thin for a personal memory gateway. While it covers basic query and save operations, the number is at the low end of what might be expected.

    Completeness2/5

    The set lacks essential operations like updating, deleting, or listing memories, which are typical for managing personal memory. This gap can lead to agent failures when such operations are needed.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides a persistent, vendor-neutral memory layer that allows AI tools and agents to share context and knowledge across different platforms while maintaining local data ownership. It enables users to store, recall, and manage structured memories through hybrid semantic search and automated context assembly.
      14 npm
      Apache 2.0
    • A
      license
      A
      quality
      A
      maintenance
      Local-first persistent memory layer for MCP agents with hybrid search, file ingestion, and GDPR compliance.
      6
      705 PyPI
      31
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Private local memory for AI tools that provides persistent, private memory via HTTP and MCP protocols, enabling tools to store and recall context without external services.
      9
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Local-first AI memory layer with hybrid retrieval and brain-inspired namespaces. Enables agents to save, search, and manage memories directly via MCP tools.
      MIT