Claude Duet connectors and memory: what carries over
Claude Duet connectors come from your Claude account, with memory and skills. Usage limits, custom MCP status, and sharing Duet's work with other agents.
Blog
Notes from building Tokenrip, the shared workspace for your AI agents.
Grok Bot memory: what Bots remember and how to share it
Grok Bot memory is kept per Bot, while all your Bots share one computer. What each Bot remembers, what a shared copy keeps, and how to share context.
Grok memory: what Grok remembers and how to share context
Grok remembers your preferences and past chats, but only inside your Grok account. How Grok memory works, how to control it, and how to share context.
Muse custom connector: add MCP to Meta Muse, share context
A Muse custom connector is built in chat, since Meta Muse has no add-MCP setting. How it works in October 2026, its limits, and how two Muses share work.
ChatGPT dots memory: what your dot remembers and shares
ChatGPT dots memory starts with your ChatGPT memories, and you cannot view or edit what your dot adds. What it keeps, how to wipe it, and how to share it.
Claude Duet vs dots vs Muse vs Grok Bot (October 2026)
Claude Duet vs dots vs Muse vs Grok Bot as of October 2026: price to start, memory, connectors and sharing compared from official pages, plus Gemini Spark.
How to add MCP to ChatGPT (2026): Plugins, Developer mode, and which plans get write tools
How to add an MCP server to ChatGPT: the Plugins flow, Developer mode, the desktop app, which plans qualify, OAuth, local servers through Secure MCP Tunnel, and the fixes for the usual problems.
Use Claude and ChatGPT together: one project both can read
How to use Claude and ChatGPT together when neither can read the other: split the work, then share one Google Doc or one MCP workspace both connect to.
Claude Code handoff: prompt, /handoff skill, and Codex
Claude Code handoff vs /compact, a copyable handoff prompt and /handoff skill, and how to pass work to a new session, Codex, Cursor or a teammate.
Claude Code memory: how it works, and why we turned auto memory off
How Claude Code memory works (CLAUDE.md vs auto memory, the 200-line limit, where files live), why we keep auto memory off, and how we share context across machines and tools instead.