Epitome Personal Portable AI Memory Vault

Created By
gunning4it4 months ago
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.
Overview

What is Epitome?
Epitome is a personal AI memory layer. It gives every AI agent you use shared, persistent memory of you — your preferences, habits, history, and relationships — stored in a knowledge graph that any MCP-compatible client can access.

No local install required. Connect via Streamable HTTP.

9 MCP Tools

ToolDescription
get_user_contextLoad your profile, top entities, and recent context. Call at the start of every conversation.
update_profileUpdate profile fields — allergies, preferences, timezone, family, job, etc. Deep-merges with existing data.
save_memorySave experiences, notes, or reflections as searchable vector memories. Automatically extracts entities into the knowledge graph.
search_memorySemantic search across saved memories using vector similarity.
add_recordLog structured data (meals, workouts, expenses, medications, habits). Tables and columns auto-create on the fly.
list_tablesDiscover what data tables exist and their schemas.
query_tableQuery records with filters or sandboxed SQL. Supports pagination and aggregations.
query_graphTraverse the knowledge graph — find relationships, patterns, and multi-hop connections.
review_memoriesDetect and resolve memory contradictions to keep data accurate.

Setup

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

Get your API key at https://epitome.fyi/dashboard/settings

Key Features

  • 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 your memory accurate
  • Per-User Isolation — each user gets their own PostgreSQL schema, not just row-level security

Server Config

{
  "mcpServers": {
    "epitome": {
      "type": "streamable-http",
      "url": "https://epitome.fyi/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}
Project Info
Created At
4 months ago
Updated At
4 months ago
Author Name
gunning4it
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Mnemom

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

13 hours ago
Docwand

13 hours ago