MCPHub

0 serversUpdated Aug 28, 2026

ServersTrendingCategories
MCPHub

Catalog

  • Servers
  • Trending
  • Categories

Company

  • About

Shout out

  • Formatly
  • Hirime

Searchable catalog of Model Context Protocol servers. Find tools that connect your AI assistant to the services and data you use.

PrivacyTerms

© 2026 MCPHub

Servers/Workplace & Productivity/ai-memory
Workplace & ProductivityOfficial
A

ai-memory

Persistent memory for any AI assistant. Zero token cost until recall. Stores memories in local SQLite, ranks by 6-factor scoring, returns results 79% smaller than JSON. Works with Claude, ChatGPT, Grok, Cursor, Windsurf, and any MCP client.

44 starsUpdated Aug 28, 2026
View on GitHub

Ads

Overview

ai-memory is a persistent memory system for AI assistants. It works with any AI that supports MCP -- Claude, ChatGPT, Grok, Llama, and more. It stores what your AI learns in a local SQLite database, ranks memories by relevance when recalling, and auto-promotes important knowledge to permanent storage. Install it once, and every AI assistant you use remembers your architecture, your preferences, your corrections -- forever. > Configuring the LLM backend (xAI Grok, OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Qwen, Mistral, Groq, Together, Cerebras, OpenRouter, Fireworks, LMStudio, vLLM, llama.cpp server, or local Ollama)? See docs/integrations/llm-backends.md — the MCP env-block recipe is the same regardless of installation path.

Installation

npm install @alphaone/ai-memory

Configuration

{
  "mcpServers": {
    "memory": {
      "command": "ai-memory",
      "args": ["--db", "~/.claude/ai-memory.db", "mcp", "--tier", "semantic"]
    }
  }

Capabilities

  • Store facts, preferences, and corrections

    ask the assistant to remember anything via `memory_store`, persisting it in a local SQLite or PostgreSQL database.

  • Recall relevant memories on demand

    retrieve context-aware results ranked by relevance using `memory_recall` or full-text `memory_search`.

  • List, retrieve, and manage stored memories

    browse all saved entries with `memory_list`, fetch a specific one by ID with `memory_get`, or archive outdated items.

  • Coordinate multi-agent workflows

    create typed action DAGs, acquire TTL-bounded leases, and exchange signed signals using the `memory_action_*`, `memory_lease_*`, and `memory_signal_*` tools.

  • Trace memory lineage and provenance

    walk the derivation DAG of any memory via `memory_lineage` to see which facts were derived from which sources.

Tags

  • anthropic
  • llm
  • ai-model
  • productivity

Related MCP servers

C

Cua

Official

MCP server for the Computer-Use Agent (CUA), allowing you to run CUA through Claude Desktop or other MCP clients.

21.9kWorkplace & ProductivityUpdated Today
N

Notion MCP

Official

Official Notion MCP server for searching, reading, creating, and updating Notion pages, databases, and workspace content from AI agents.

4.6kWorkplace & ProductivityUpdated Jul 25, 2026

Notion MCP Server

Search pages, read blocks, and create content in Notion workspaces.

3.9kWorkplace & ProductivityUpdated 3 days ago
L

Laravel Boost

Official

Laravel Boost is an MCP server equipped with over 15 specialized tools designed to streamline AI-assisted coding workflows.

3.6kWorkplace & ProductivityUpdated Today