Guides: memory for personal AI agents
Morphika is secure, shared memory for personal AI agents like Claude Code, Codex and Claude Desktop. These guides explain how memory for AI agents works, how to keep it secure, and how to set it up in the agents you use.
All guides
What is memory for AI agents?
What agent memory is, the kinds (session, persistent, personal, shared), and why memory for personal AI agents needs security.
How to share one memory between Claude Code, Codex and Claude Desktop
Connect Claude Code, Codex and Claude Desktop to the same memory, so something you tell one agent the others already know.
How to keep an AI agent's memory secure
The risks to AI agent memory (poisoning, prompt injection, leaked secrets, silent edits) and the controls that stop each one.
Memory and security for personal AI agents like Muse and Instinct
How personal AI agents like Meta Muse and Instinct remember you, the security questions to ask any agent that holds your memory, and where Morphika fits.
How does Meta Muse's memory work, and can it use outside memory?
How Meta Muse's memory works, how to view and delete it, how Muse connectors and MCP work, and whether Muse can use Morphika.
Instinct AI and memory: what it keeps and how to stay safe
What the Instinct personal AI agent stores, the privacy and security concerns reported since launch, and questions to ask before you connect your accounts.
How to give Claude Code persistent, secure memory
How Claude Code's CLAUDE.md and auto memory work, and how to add persistent, shared, secure memory with one claude mcp add command.
How to give OpenAI Codex persistent, secure memory
How AGENTS.md and Codex memories work, and how to connect Codex to persistent, shared, secure memory with codex mcp add.
How to add secure, shared memory to Claude Desktop
Add Morphika to Claude Desktop or claude.ai as a custom connector, so the Claude app shares memory with Claude Code and Codex.
What is an MCP memory server?
What an MCP memory server is, remote vs local, how OAuth sign-in works, and Morphika's full-access and read-only addresses and tools.
How can a team's AI agents share memory safely?
Workspaces, one-time invite codes, and why every change to a team's shared agent memory waits for another member's approval.
About Morphika
How Morphika keeps agent memory secure
Morphika's security model: approvals, Face ID, the hash-chained audit log, OAuth sign-in, credential blocking, what is stored where, and deletion.
Morphika: frequently asked questions
Short, factual answers about what Morphika is, which agents it works with, approvals, security, privacy, deletion and how to get access.
About Morphika
Who builds Morphika (Trixode Studios Inc.), why, and how to reach us.
Last updated