Memory & knowledge
Keeping what a team and its agents know, across sessions and after people leave.
6 answers · 18 articles · 3 definitions
Definitions in this subject
Can Claude and Meta's Muse share one memory?
Yes, by connecting both to the same store. Claude adds it as an MCP connector. Muse, as of September 2026, builds a custom connector when you ask and give it the address, then takes a key through a secure prompt. A Wire container works with both. Keep them separate when nothing you tell one is worth the other knowing.
AnswerCan Claude and ChatGPT share one memory?
Neither product can read the other's memory. Claude's memory and ChatGPT's memory are per-account and per-vendor, and no setting connects them. The cheapest option is a document you attach in both assistants. A store that both read and write over MCP, such as a Wire container, stays current as what you are planning changes.
ArticleAI memory lock-in works until it blocks your own product
Anthropic merged Claude chat and Cowork memory on August 25, 2026. AI memory lock-in is a moat until it stands between a vendor and its own next product.
ArticleHow to Move Your AI Context Between Tools
Claude now imports ChatGPT memories, but conversation history, files, and team context still don't transfer. Here's what actually moves and what doesn't.
AnswerIs ChatGPT's memory enough for a team?
ChatGPT's memory is enough for one person and stops there. OpenAI ties it to an individual account and says it is not transferable to other users, even inside the same Business workspace. There is no API access to it. A workspace owner can only switch it off, which deletes what members saved.
AnswerIs Claude's memory enough for a team?
Claude's memory is enough for one person, not for a team. It is tied to your account, so a teammate's Claude cannot read it and neither can any other assistant. Anthropic turns it off by default on Team and Enterprise, and owners cannot view what members store.
AnswerConnecting company data to AI agents: how to choose
Pick by where the data lives, not by which protocol looks strongest. If it sits inside one product that ships a connector, use that. If it is spread across a wiki, a drive, and a CRM that agents read daily, one place has to unify and structure it first, or every agent re-solves the same problem.
AnswerKnowledge transfer when an engineer leaves: what to capture
Capture the decisions, not the documentation. What leaves with a senior engineer was never written down: it lived in tradeoffs, rejected approaches, and incident history. Documentation mandates fail because writing docs is unrewarded work that competes with shipping. What survives a departure is knowledge captured as a byproduct of work already happening, somewhere the next person's tools can read.
ArticleGhost memory: why agents can't tell what's true now
Ghost memory is when old, current, and changed facts sit in an agent's memory and get retrieved together. Deleting loses history. Labeling the edge works.
ArticleKimi K3's 1M context runs mostly on linear attention
Kimi K3's 1M-token window runs on Kimi Delta Attention: hybrid linear attention with a fixed-size state. Why cheap long context still needs context curation.
ArticleDemand paging for the AI context window
A 2026 systems paper found 21.8% of tokens in agent context windows are wasted. Demand paging treats the AI context window as L1 cache, not full memory.
ArticleClaude Fable 5 put a price on context portability
Claude Fable 5 returns refusals as HTTP 200s and retries them on Opus 4.8. The fallback API reveals exactly what agent context survives a mid-task model swap.
Give your agents one place to read and write.
Put in your docs, data and notes, then connect Claude, Codex or anything else with one link.
Create a container