MCP.so
ログイン

Octopoda Memory MCP Server

@RyjoxTechnologies

基本情報

カテゴリ

生産性

トランスポート

stdio

作者

RyjoxTechnologies

投稿者

Joseph Roberts

Octopoda Memory MCP Server について

Persistent memory for AI agents that survives across sessions. Store, recall, and semantically search memories. Includes loop detection that catches agents stuck repeating themselves, full audit trails, shared memory between agents, and a real-time dashboard. Works with Claude Co

Octopoda Memory MCP Server の設定

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": {
    "octopoda": {
      "command": "python",
      "args": [
        "-m",
        "synrix_runtime.api.mcp_server"
      ],
      "env": {
        "OCTOPODA_API_KEY": "your-key-from-octopodas.com"
      }
    }
  }
}

Octopoda Memory MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Octopoda Memory?

Octopoda Memory is a persistent memory system for AI agents. It allows agents to store, recall, and search memories that survive across sessions, restarts, crashes, and deployments. It is designed for developers building AI agents that need long-term memory, shared knowledge, and monitoring capabilities.

How to use Octopoda Memory?

Install the package with pip install octopoda, obtain a free API key from https://octopodas.com, then add it to Claude Code using the command: claude mcp add octopoda -s user -e OCTOPODA_API_KEY=your-key -- python -m synrix_runtime.api.mcp_server.

Key features of Octopoda Memory

  • Persistent memory that survives restarts, crashes, and deployments
  • Semantic search to find memories by meaning
  • Loop detection to catch agents repeating themselves
  • Audit trail logging every decision with reasoning
  • Shared memory for agents to share knowledge through memory spaces
  • Real-time dashboard to monitor all agents at localhost:7842

Use cases of Octopoda Memory

  • Storing agent memories that persist across multiple sessions
  • Searching for past memories by semantic similarity rather than exact keys
  • Preventing agents from burning tokens by repeating the same actions
  • Logging and reviewing agent decision rationale for debugging
  • Enabling multiple agents to share and access common knowledge

よくある質問

1

What is Octopoda Memory?

Octopoda Memory provides persistent memory for AI agents, allowing them to store, recall, and search memories that survive across sessions.

2

How do I install Octopoda Memory?

Install it via pip: `pip install octopoda`. Then get a free API key at https://octopodas.com and add the server to Claude Code with the provided command.

3

What tools does Octopoda Memory provide?

It offers 13 tools including octopoda_remember, octopoda_recall, octopoda_recall_similar, octopoda_search, octopoda_recall_history, octopoda_snapshot, octopoda_restore, octopoda_share, octopoda_read_shared, octopoda_list_agents, octopoda_agent_stats, octopoda_log_decision, and octopoda_loop_status.

4

What is the real-time dashboard address?

The real-time dashboard runs at localhost:7842.

5

Where do I get an API key?

A free API key is available at https://octopodas.com.

コメント

「生産性」の他のコンテンツ