Epitome
io.github.gunning4itPublished by GitHub account gunning4itv1.0.0Updated Oct 25, 2026
Personal AI memory — gives every AI agent shared, persistent memory of you
Overview
Epitome is a hosted personal memory layer that gives AI assistants a shared, persistent profile of you through recall, memorize and review tools.
- What you can do
- Recall stored personal memories and profile context across agents and sessions, avoiding repeated introductions and preferences each time. Save new memories so they persist and are shared with other connected agents. Review and manage stored memory, with confidence scoring, source attribution and lifecycle handling. Build on a structured profile, vector semantic memory, key-value storage and a knowledge graph of people, places and concepts.
- When to use it
- Use it when you want several different AI assistants to remember the same facts about you, such as preferences, allergies, tech stack or routines, instead of starting each conversation from zero. Also suited to developers building agents that need persistent per-user memory.
- Requirements
- A remote MCP endpoint at epitome.fyi over Streamable HTTP, or a self-hosted Docker Compose deployment with Node.js 22, PostgreSQL 17 with pgvector, and Google or GitHub OAuth. A bearer API key is required in the Authorization header, obtained from the dashboard settings after signing up.
Installation
In SourceWeft
- Open Epitome in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.gunning4it%2Fepitome-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"epitome": {
"type": "http",
"url": "https://epitome.fyi/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
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.
[MIT License] [GitHub Stars] [Tests]
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
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:
Claude Code
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?
The Five Layers
Architecture
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
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.
Then open a PR — we're happy to help with your first contribution.
License
Source: README.md at commit 315813d
Tools
0Version history
1- v1.0.0LatestSep 16, 2026
Score
60% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts