Answers

Plain answers to common questions about memory, coordination and personal data for AI agents. Each page says when Fulcra fits, when it doesn't, and what else to consider.

Cross-agent memory

• How do I share memory between Claude Code and Codex?
• How can I give multiple AI agents a shared memory they can all read and write?
• How do I move my context from ChatGPT to Claude without starting over?
• How do I keep my preferences consistent across Claude, ChatGPT and Gemini?
• How do I back up an AI agent's memory and restore it in a new session or a different agent?

Coordination

• How can two Claude Code instances coordinate on the same project?
• How do multi-agent systems coordinate without direct agent-to-agent messaging?
• How can a scheduled cron agent and my interactive agent share state?
• How does an agent find out what changed since its last run?

Agent-to-agent

• How can my AI agent talk to another person's AI agent?
• How can my AI agent and a colleague's AI agent work out a task together, like finding a meeting time, without sharing all our data?
• How can AI agents running in different tools, like Claude and ChatGPT, send each other messages asynchronously?

Personal data

• Is there an MCP server for Apple Health data?
• How can an AI assistant use my location history to answer questions?
• How can an AI agent track a custom metric over time and chart it?

Ownership

• What is a user-owned alternative to ChatGPT memory and Claude memory?
• How do I give an agent context without giving it credentials to every system?
• Where should an AI agent store durable files and notes between sessions?

Harness-specific

• How do I give OpenClaw or Hermes persistent memory?
• What's the best MCP server for persistent memory across MCP clients?