Skip to main content
Glama

English | العربية | 简体中文 | Español

🧠 Local AI Memory Bridge

Persistent, encrypted, fully offline long-term memory for AI agents (Claude Code, Cursor, and any MCP client). Your memories never leave your machine.

⚠️ Status: alpha (v0.1). Save, search, redaction and the MCP server are tested from the CLI and a test MCP client. Not yet tested with every agent. compact has had limited testing. Do not rely on it for highly sensitive data yet.

Why

  • 🔒 Whole-database encryption (SQLCipher) plus AES-256-GCM on every memory text

  • 🔑 Master key in your OS keychain (falls back to a chmod 600 key file where no keychain exists, e.g. Codespaces or Docker)

  • 🧹 Secrets redacted before anything is embedded or stored (API keys, tokens, passwords, JWTs, private keys, credit cards, emails)

  • 🌍 Multilingual semantic search (multilingual-e5-small, 100+ languages including Arabic), running locally via ONNX

  • 🔌 Native MCP server over stdio

Related MCP server: aci-mcp

Architecture

flowchart LR
  A[AI Agent<br/>Claude Code / Cursor] -- MCP stdio --> B[MCP Server]
  B --> C[PII Redaction<br/>regex + entropy]
  C --> D[Local Embeddings<br/>e5-small ONNX]
  D --> E[(SQLCipher DB<br/>sqlite-vec + AES-GCM text)]
  K[OS Keychain] -. master key .-> E
  E --> F[Compaction<br/>cluster + dedupe]

Quick Start

Requires Node.js 20 or newer.

npx -y local-ai-memory-bridge add "I prefer TypeScript for new projects"
npx -y local-ai-memory-bridge search "what language do I prefer?"
npx -y local-ai-memory-bridge setup

The first add or search downloads the embedding model (about 100-150 MB) to ~/.memory-bridge/models. Run one of them once before connecting an agent, so the agent does not time out on the first call.

Connect to Claude Code

claude mcp add memory-bridge -- npx -y local-ai-memory-bridge serve
claude mcp list

Connect to Cursor (mcp.json)

{
  "mcpServers": {
    "memory-bridge": {
      "command": "npx",
      "args": ["-y", "local-ai-memory-bridge", "serve"]
    }
  }
}

CLI

Command

Description

serve

Run the MCP server (stdio)

add <text> [-p project]

Save a memory (redacted automatically)

search <query> [-n 5] [-p project]

Semantic search

forget <id>

Delete a memory

compact [-d 30] [-t 0.93]

Merge near-duplicate memories older than N days

stats

Show counts and DB path

setup

Print MCP config snippets

MCP Tools

Tool

Input

Purpose

memory_save

text, project?

Store a durable fact or decision

memory_search

query, limit?, project?

Semantic recall

memory_forget

id

Delete a memory

Configuration

Env var

Default

Meaning

MEMORY_BRIDGE_HOME

~/.memory-bridge

Data directory

MEMORY_BRIDGE_KEY

(unset)

64-char hex master key override

MEMORY_BRIDGE_MODEL

Xenova/multilingual-e5-small

Embedding model

MEMORY_BRIDGE_MARGIN

0.04

Relevance cut-off relative to the best hit

Your encryption key (read this)

Your memories can only be opened with the master key.

  • If the OS keychain entry is deleted, or you move to a new machine without the key, the database cannot be opened and the data is unrecoverable.

  • You will see: Cannot decrypt memory.db: the master key does not match.... Either restore your key via MEMORY_BRIDGE_KEY, or delete ~/.memory-bridge/memory.db to start fresh.

  • To control the key yourself, generate one (openssl rand -hex 32), store it in a password manager, and set it as MEMORY_BRIDGE_KEY.

  • In ephemeral environments (Codespaces, containers), the key and database may be lost when the environment is deleted.

Security model and limits

  • Redaction is best-effort (patterns plus entropy). It will miss some secrets, so don't rely on it as your only control.

  • This protects data at rest on your machine, not against malware running as your user.

  • This project has not had an independent security review.

Roadmap

  • One-command install via npm (npx)

  • Key export / backup command

  • Optional NER-based PII detection

  • Optional local-LLM summarization (Ollama)

  • Tests and CI

License

MIT

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Provides a local-first, provenance-aware memory layer that enables MCP-capable AIs to store, recall, validate, and reason over facts with contradiction detection, trust weighting, deduplication, and encryption, supporting offline private operation without GPUs or API keys.
      9
      Apache 2.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides AI agents with persistent local memory management, including semantic recall, knowledge graph traversal, and automatic memory consolidation, enabling structured long-term memory across MCP clients.
      Apache 2.0
    • A
      license
      A
      quality
      C
      maintenance
      Provides persistent local memory for any MCP-compatible AI agent, enabling agents to store, search, recall, forget, export, and manage preferences, rules, and facts with zero dependencies, no cloud, and no API keys.
      8
      MIT