AI Memory Vault
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AI Memory Vault
One memory for all your AI apps. Save something in ChatGPT, and Claude knows it seconds later.
Every AI app keeps its own memory, and none of them share it: tell ChatGPT you moved house and
Claude still doesn't know. Vault fixes that. It's a small memory server you host yourself, and
Claude, ChatGPT and Claude Code connect to it as an MCP connector. It keeps your facts, chats,
documents and projects in one place, and gives each app only the few pieces a question needs
instead of your whole history. It runs on Cloudflare's free tier, or on any computer with Node or
Docker. To see the exact Cloudflare setup I run myself, check the
cloudflare-reference branch.

▶ Watch the 87-second video (4K, portrait for phones)
What it does
Save: "Save to Vault: …", "Update Vault: …", "Forget …". Apps also save lasting things on their own.
Recall: before a personal answer, the app asks Vault and gets a short list of the most relevant facts.
Search old chats: "What did I ask ChatGPT about car hire?" finds it, even in different words.
Never loses anything: an update keeps the old version, and the database refuses deletes.
Related MCP server: Recall
How it works
A save is written and answered at once ("Saved ✓"). The chat never waits.
In the background, an AI model adds the item to a knowledge graph (who and what it's about, and how they connect) and a meaning index (so "car" finds "Fiat Panda").
A question runs four searches at once: keywords, meaning, graph and project. The results are merged and sent back as a few short lines.
More detail: how Vault works.
Tested, not guessed
Every change was measured with the same exam: questions whose answers are known facts, scored by
whether those facts come back. My questions are private, but the exam runner is in
evals/ so you can write your own.
Step | Answers found | Reply size |
Keyword search only | 65% | ~1,600 tokens |
+ knowledge graph | 55% | ~400 tokens |
+ meaning search | 83% | ~600 tokens |
+ tidier replies and categories | 94% | ~600 tokens |
There's also a full test suite (npm test), and a live check that saves, updates and forgets
made-up items through a real connection (13 / 13 passed).
Quick start
Let your AI set it up. Paste this into Claude Code or Codex:
Set up Vault for me by following https://raw.githubusercontent.com/Tejas94/ai-memory-vault/main/SETUP.mdIt asks you a few questions, runs the steps, and stops whenever something needs you (a sign-in, a password). It can also help you bring in your own notes and documents.
Or do it yourself:
On any computer (Node 22.16 or newer: 22, 24 and 26 are tested). No account needed:
npm install
cp .env.example .env # then set VAULT_KEY to a long random secret
npm run start:node # Vault is at http://localhost:8788/mcpOr with Docker: docker build -t vault ., then run it with your .env.
Full steps, sign-in and AI models: setup.
On Cloudflare's free tier: put your own database ids in wrangler.jsonc, set your secrets
and deploy. See setup.
Then connect your first app: connect your apps.
Docs
Set up and run: install, deploy, catch up, fix problems
Connect your apps: Claude, ChatGPT, Claude Code, and your first fact
How it works: saving, searching, the rules, and why it's built this way
Built with
TypeScript, the official MCP SDK, Cloudflare Workers, D1, Workers AI and Vectorize, or Node with SQLite files.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Your own memory inside ChatGPT and Claude, with the source of every note.
Shared memory for AI tools: save once, recall word for word from Claude, ChatGPT, Codex or Gemini.
Private memory for AI agents: save and recall facts across Claude Code, Codex, Cursor and ChatGPT.
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI apps such as Claude, ChatGPT, Cursor, VS Code and Codex to share one searchable memory, so a fact told to one app can be recalled in another with the exact line, speaker and date it came from. Users sign in per app and can allow read-only or read-and-write access, saving, correcting or forgetting memories and disconnecting apps at any time.MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude and other AI agents to store decisions, patterns, and knowledge in persistent cross-session memory that survives restarts and context compaction, then retrieve relevant context automatically in future conversations. Supports self-hosting on Redis or Valkey, or a managed cloud service, with workspace organization, team sharing, and configurable embedding providers.17 npmMIT
- AlicenseNot gradedqualityAmaintenanceGives Claude and other AI agents persistent cross-session memory, so stored decisions, code patterns, and knowledge are automatically retrieved in future conversations and survive restarts and context compaction. It can be run self-hosted on your own Redis or Valkey instance or used as a managed cloud service.17 npmMIT
- AlicenseNot gradedqualityAmaintenanceProvides persistent cross-session memory for Claude and other AI agents, letting users store decisions, code patterns, and knowledge once and have relevant context retrieved automatically in future conversations. Memories survive context limits, restarts, and compaction, and can be organized by workspace or shared across a team when self-hosted on Redis/Valkey or used via the managed cloud service.17 npmMIT