Epitome
공식Personal AI memory — gives every AI agent shared, persistent memory of you
Epitome
One memory layer, every AI agent.
The portable identity layer that gives every AI agent a shared, persistent memory of you.
Open source. Self-hostable. Yours.
Website · Quickstart · Connect an Agent · Docs · Contributing
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)
- Sign up at epitome.fyi
- Go to Settings → API Keys and copy your MCP URL
- Connect an AI agent — done
Self-Hosted
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:
{
"mcpServers": {
"epitome": {
"url": "https://epitome.fyi/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Claude Code
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 History | Vector DB | Note Apps | Epitome | |
|---|---|---|---|---|
| Portable identity | ✓ | |||
| Multi-agent shared memory | ✓ | |||
| Knowledge graph | ✓ | |||
| Consent & audit per agent | ✓ | |||
| Per-user schema isolation | ✓ | |||
| Structured + semantic data | partial | ✓ | ||
| Self-hostable | ✓ | ✓ |
The Five Layers
| # | Layer | Description |
|---|---|---|
| 01 | Personal Database | Structured tables, vector semantic memory, and key-value storage. Your data lives in PostgreSQL — queryable, exportable, yours. |
| 02 | Portable Identity | A structured profile any AI agent reads instantly. Name, preferences, relationships — zero cold start, every conversation. |
| 03 | Memory Quality | Confidence scoring, source attribution, and lifecycle management. Memories earn trust through reinforcement, not blind faith. |
| 04 | Knowledge Graph | Entities with typed, weighted edges. People, places, concepts — connected in a graph that grows with every interaction. |
| 05 | Consent & Audit | Per-table permissions and an append-only activity log. You control exactly what each agent can see and do. |
Architecture
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
| Component | Technology |
|---|---|
| Runtime | Node.js 22 LTS |
| API | Hono |
| Database | PostgreSQL 17 + pgvector |
| MCP | @modelcontextprotocol/sdk |
| Frontend | React 19 + Tailwind CSS 4 + shadcn/ui |
| Validation | Zod |
| Testing | Vitest |
Documentation
- Quick Start — Get running in minutes
- JavaScript SDK — Build with
@epitomefyi/sdk - npm Package — Install and version history
- AI SDK Tools —
searchMemory,saveMemory,getUserContextfor tool-calling - API Reference — REST endpoint documentation
- MCP Tools — All 3 MCP tools explained
- Architecture — Full technical specification
- Data Model — Every table, column, and constraint
- Self-Hosting Guide — Docker Compose deployment
- Security — Isolation, consent, and audit
Contributing
Contributions are welcome! See CONTRIBUTING.md for guidelines.
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
관련 서버
Nodit MCP Server
Provides structured, context-ready blockchain data across multiple networks through Nodit's Web3 infrastructure.
MCP Memory libSQL
A persistent memory system for MCP using libSQL, providing vector search and efficient knowledge storage.
Enhanced Medication Information MCP Server
Provides real-time access to FDA drug data, including shortages, labeling, and recalls, via the openFDA API.
MCP KQL Server
Execute KQL queries using Azure authentication. Requires Azure CLI login.
MRC Data
China apparel supply chain data infrastructure for AI agents — 3,000+ verified suppliers, 350+ lab-tested fabrics, 170+ industrial clusters across 31 provinces. MCP + REST + OpenAPI.
FHIR MCP Server by CData
A read-only MCP server for FHIR, enabling LLMs to query live FHIR data. Requires the CData JDBC Driver for FHIR.
PostgreSQL MCP Server
An MCP server for exploring and querying PostgreSQL databases.
Apache AGE MCP
MCP server for Apache AGE graph databases on PostgreSQL. **21 MCP tools** — the most comprehensive Apache AGE MCP server (graph CRUD, Cypher queries, batch transactions, semantic search, Graph RAG, vis.js visualization, export/import) - **F#/.NET** — the only non-Python Apache AGE MCP server, installs as a single dotnet tool - **Production-grade** — BenchmarkDotNet-verified performance (cached queries in 62 ns, Cypher in 1 ms) - **Open source** — MIT license, published on [NuGet](https://www.nuget.org/packages/AgeMcp) - **Documentation** — full docs site at neftedollar.com/age-mcp
ThoughtSpot MCP Server
Securely query and retrieve data from your ThoughtSpot instance.
Adobe Commerce MCP Server by CData
A read-only MCP server for Adobe Commerce, enabling LLMs to query live data using the CData JDBC driver.