Skip to content
MCP server

Apiary Memory

Local-first shared memory for AI agents where only you confirm what is saved

Runs locallyStatus and history
Pricing
Free
Platforms
macOS, iOS, CLI
Runs
Locally
Version
0.2.5
Listing updated
3 days ago

About Apiary Memory

Apiary Memory is a free MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

Several AI clients can share one memory that lives on your own computer instead of with each vendor. Agents can only propose candidates; writing to the official memory needs your approval in the app, which the site frames as a governance rule rather than a setting.

Retrieval blends keyword and semantic ranking, using a roughly 100 MB model installed locally, so queries stay on the machine and fall back to keyword search if the model fails. Passwords, keys and bank cards go into a local encrypted area. The site gives 54 ms hot search on 1,485 memories and says it handles a million at about 0.6 seconds.

The desktop app is free on the Mac App Store, iOS is listed, and Windows and Linux are marked coming soon. The MCP server is also on PyPI as apiary-memory, with local, auto and remote modes. The site is in Chinese.

Install

Run in a terminal

claude mcp add apiary-memory --env HIVE_AGENT_TOKEN='<HIVE_AGENT_TOKEN>' -- uvx apiary-memory

Add to claude_desktop_config.json

{
  "mcpServers": {
    "apiary-memory": {
      "command": "uvx",
      "args": [
        "apiary-memory"
      ],
      "env": {
        "HIVE_AGENT_TOKEN": "<HIVE_AGENT_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "apiary-memory": {
      "command": "uvx",
      "args": [
        "apiary-memory"
      ],
      "env": {
        "HIVE_AGENT_TOKEN": "<HIVE_AGENT_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "apiary-memory": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "apiary-memory"
      ],
      "env": {
        "HIVE_AGENT_TOKEN": "<HIVE_AGENT_TOKEN>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "apiary-memory": {
      "command": "uvx",
      "args": [
        "apiary-memory"
      ],
      "env": {
        "HIVE_AGENT_TOKEN": "<HIVE_AGENT_TOKEN>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "apiary-memory": {
      "command": "uvx",
      "args": [
        "apiary-memory"
      ],
      "env": {
        "HIVE_AGENT_TOKEN": "<HIVE_AGENT_TOKEN>"
      }
    }
  }
}

Configuration

  • HIVE_MODEauto (default) asks the Hive app and falls back to the local store only when the app is unreachable; local never touches the network; remote refuses to fall back.
  • HIVE_DBPath to the local memory database. Defaults to ~/.memory-hive/hive.db. Only used when the local store answers.
  • HIVE_AGENT_IDAgent id issued by your own Hive app. Only needed for calls the app serves (HIVE_MODE=auto with the app running, or remote). Not required to use the local store.
  • HIVE_AGENT_TOKENAccess token issued by your own Hive app when the agent is registered. Only needed for calls the app serves.
  • HIVE_MCP_URLHive app MCP endpoint. Defaults to http://127.0.0.1:8768/mcp

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

recall
Search saved memory.
propose
Submit a candidate memory for approval.
manage
Manage stored memory.
get_context
Fetch your context when an agent connects.
say
Post to the collaboration board.
board
Read the collaboration board.

What it does

Propose, then confirm
Agents submit candidates; you approve them before they become memory.
Local storage
Data stays in a local database, with no account or telemetry.
Hybrid search
Keyword and semantic ranking fused, with fallback to keywords.
Encrypted private area
Keeps passwords, keys and cards in local encryption.
Agent board
A shared board shows which agent is doing what.
Backup and export
Whole-library backup, migration and standard-format export.

Good for

  • Carry context from one AI client to another
  • Keep notes and preferences off vendor servers
  • Review what an agent wants to remember
  • Search years of saved notes offline

Pricing

Free

Mac App Store app is free; other platforms coming

Prices change. Check hello-fengchao.com before you buy.

Apiary Memory FAQ

Can an agent write memory directly?

No. Agents propose candidates and you confirm.

Which tools does it expose?

recall, propose, manage, get_context, say and board.

Does it need an account?

No. The site says no account, no telemetry and no cloud by default.

Is Apiary Memory free?

Yes. Apiary Memory is free to use.

How do I add Apiary Memory to Claude Code?

Run this command in your terminal: claude mcp add apiary-memory --env HIVE_AGENT_TOKEN='<HIVE_AGENT_TOKEN>' -- uvx apiary-memory

What are the best alternatives to Apiary Memory?

The closest alternatives to Apiary Memory are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to Apiary Memory

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity