Epitome

AI 与智能体

by gunning4it

Personal AI memory — gives every AI agent shared, persistent memory of you

什么是 Epitome

Personal AI memory — gives every AI agent shared, persistent memory of you

README

<p align="center"> <img src="dashboard/public/epitome.png" alt="Epitome" width="80" /> </p> <h1 align="center">Epitome</h1> <p align="center"> <strong>One memory layer, every AI agent.</strong> </p> <p align="center"> The portable identity layer that gives every AI agent a shared, persistent memory of you.<br /> Open source. Self-hostable. Yours. </p> <p align="center"> <a href="https://github.com/gunning4it/epitome/blob/main/LICENSE"><img src="https://img.shields.io/github/license/gunning4it/epitome" alt="MIT License" /></a> <a href="https://github.com/gunning4it/epitome/stargazers"><img src="https://img.shields.io/github/stars/gunning4it/epitome" alt="GitHub Stars" /></a> <a href="https://github.com/gunning4it/epitome/actions"><img src="https://img.shields.io/github/actions/workflow/status/gunning4it/epitome/ci.yml?branch=main&label=tests" alt="Tests" /></a> </p> <p align="center"> <a href="https://epitome.fyi">Website</a> · <a href="#quickstart">Quickstart</a> · <a href="#connect-an-ai-agent">Connect an Agent</a> · <a href="https://epitome.fyi/docs">Docs</a> · <a href="#contributing">Contributing</a> </p>

The Problem

Every AI conversation starts from zero. You repeat yourself to every agent — your name, your preferences, your allergies, your tech stack. Chat history is siloed per app. There's no portable memory layer.

Epitome fixes this. One database that every AI agent shares, so they all remember you.


Quickstart

Hosted (fastest)

  1. Sign up at epitome.fyi
  2. Go to Settings → API Keys and copy your MCP URL
  3. Connect an AI agent — done

Self-Hosted

bash
git clone https://github.com/gunning4it/epitome.git
cd epitome
cp .env.example .env    # edit with your credentials
docker compose up -d

Open localhost:5173 and sign in with Google or GitHub OAuth.


Connect an AI Agent

Get your API key from Settings → API Keys in the dashboard (hosted or self-hosted).

Claude Desktop

Add to your claude_desktop_config.json:

json
{
  "mcpServers": {
    "epitome": {
      "url": "https://epitome.fyi/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Claude Code

bash
claude mcp add --transport http --header "Authorization: Bearer YOUR_API_KEY" epitome https://epitome.fyi/mcp

Self-Hosted

For self-hosted, replace https://epitome.fyi with http://localhost:3000.

Epitome exposes 3 MCP tools — recall, memorize, and review. See the full tool reference.


Who This Is For

  • AI developers building agents that need persistent user memory
  • Power users who want every AI to remember them across platforms
  • Self-hosters who want full data ownership — no cloud required

Use Cases

  • Your meal-tracking agent remembers your allergies
  • Your coding assistant knows your stack, your patterns, your team
  • Your calendar agent knows your family, your priorities, your routines
  • Every new AI tool you try already knows you on day one

Why Epitome?

Chat HistoryVector DBNote AppsEpitome
Portable identity
Multi-agent shared memory
Knowledge graph
Consent & audit per agent
Per-user schema isolation
Structured + semantic datapartial
Self-hostable

The Five Layers

#LayerDescription
01Personal DatabaseStructured tables, vector semantic memory, and key-value storage. Your data lives in PostgreSQL — queryable, exportable, yours.
02Portable IdentityA structured profile any AI agent reads instantly. Name, preferences, relationships — zero cold start, every conversation.
03Memory QualityConfidence scoring, source attribution, and lifecycle management. Memories earn trust through reinforcement, not blind faith.
04Knowledge GraphEntities with typed, weighted edges. People, places, concepts — connected in a graph that grows with every interaction.
05Consent & AuditPer-table permissions and an append-only activity log. You control exactly what each agent can see and do.

Architecture

code
AI Agent ──→ MCP (Streamable HTTP) ──→ Hono API ──→ PostgreSQL
                                         │
                                    per-user schema
                                      isolation

Each user gets their own PostgreSQL schema (user_{id}) — not row-level security, full schema-level isolation. Cross-schema access is impossible at the SQL level.

See EPITOME_TECH_SPEC.md for the full architecture.


Security & Privacy

  • You own your data — self-host or use the hosted service
  • Per-user PostgreSQL schema isolation — not row-level security, full schema separation
  • Per-agent consent rules — you control what each agent can read and write
  • Append-only audit log — every access is recorded
  • GDPR-ready — export or delete all your data at any time

Tech Stack

ComponentTechnology
RuntimeNode.js 22 LTS
APIHono
DatabasePostgreSQL 17 + pgvector
MCP@modelcontextprotocol/sdk
FrontendReact 19 + Tailwind CSS 4 + shadcn/ui
ValidationZod
TestingVitest

Documentation


Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

bash
git clone https://github.com/gunning4it/epitome.git
cd epitome && cp .env.example .env
docker compose up -d

Then open a PR — we're happy to help with your first contribution.


License

MIT

常见问题

Epitome 是什么?

Personal AI memory — gives every AI agent shared, persistent memory of you

相关 Skills

Claude接口

by anthropics

Universal
热门

面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。

想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心

AI 与智能体
未扫描109.6k

提示工程专家

by alirezarezvani

Universal
热门

覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。

把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。

AI 与智能体
未扫描9.0k

智能体流程设计

by alirezarezvani

Universal
热门

面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。

帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。

AI 与智能体
未扫描9.0k

相关 MCP Server

顺序思维

编辑精选

by Anthropic

热门

Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。

这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。

AI 与智能体
82.9k

知识图谱记忆

编辑精选

by Anthropic

热门

Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。

帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。

AI 与智能体
82.9k

PraisonAI

编辑精选

by mervinpraison

热门

PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。

如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。

AI 与智能体
6.4k

评论