广告合作
MCP.so
登录

Epitome Personal Portable AI Memory Vault MCP Server

@gunning4it

代码仓库

基本信息

分类

记忆与知识

传输方式

stdio

作者

gunning4it

提交者

Josh G

关于 Epitome Personal Portable AI Memory Vault MCP Server

Epitome gives every AI agent shared, persistent memory of you. It stores memories, facts, and preferences in a personal knowledge graph, so any AI tool you use already knows your context. Connect via MCP using Streamable HTTP — no local install needed.

#memory#knowledge-graph#ai-agent#mcp#personalization

Epitome Personal Portable AI Memory Vault MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "epitome": {
      "type": "streamable-http",
      "url": "https://epitome.fyi/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

Epitome Personal Portable AI Memory Vault MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,直接连接服务器端点实时获取工具列表。

概览

What is Epitome?

Epitome is a personal AI memory layer that gives every AI agent you use shared, persistent memory of your preferences, habits, history, and relationships — stored in a knowledge graph accessible by any MCP-compatible client. No local install is required; it connects via Streamable HTTP.

How to use Epitome?

Configure an MCP client with a streamable-http transport pointing to https://epitome.fyi/mcp and an API key in the authorization header. Obtain your API key from https://epitome.fyi/dashboard/settings. After setup, invoke any of the nine provided tools (e.g., get_user_context at conversation start, save_memory to store notes).

Key features of Epitome

  • Knowledge graph — entities and relationships extracted automatically from every interaction
  • Semantic search — vector-powered memory recall across all saved content
  • Structured data — track anything with auto-created tables and columns
  • Contradiction detection — automatic quality checks keep memory accurate
  • Per-user isolation — each user gets their own PostgreSQL schema

Use cases of Epitome

  • Provide every AI agent with your profile and recent context at conversation start
  • Log structured data like meals, workouts, expenses, or medications without manual schema setup
  • Save and search personal notes, reflections, or experiences via vector memory
  • Traverse relationship patterns (e.g., multi-hop connections) across your knowledge graph
  • Review and resolve memory contradictions to maintain data accuracy

常见问题

1

How do I get an API key for Epitome?

Sign in at [https://epitome.fyi/dashboard/settings](https://epitome.fyi/dashboard/settings) to generate your API key.

2

Does Epitome require local installation?

No. Epitome runs as a cloud service and connects via Streamable HTTP — no files to install or servers to run locally.

3

Where is my data stored?

Each user gets their own PostgreSQL schema, ensuring per-user isolation. Data is stored on Epitome's servers.

4

What transport does Epitome use?

Epitome uses the MCP Streamable HTTP transport. Configure your client with type `"streamable-http"` and the URL `https://epitome.fyi/mcp`.

5

How many tools does Epitome provide?

Epitome provides nine MCP tools: `get_user_context`, `update_profile`, `save_memory`, `search_memory`, `add_record`, `list_tables`, `query_table`, `query_graph`, and `review_memories`.

评论

记忆与知识 分类下的更多 MCP 服务器

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

priostack

ideaswave

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

Semantic Ui React

Semantic-Org

The official Semantic-UI-React integration

13.2K

server-noonien - shared memory MCP

sequico

Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K
广告合作