Journal
Notes on memory for AI assistants — how it works, where it is stored, and what the trade-offs actually cost.
- 30 October 2026 · 6 min read
Claude memory: what Claude remembers from one chat to the next
Claude has a built-in memory and can search your past chats. What it keeps, on which plan, where to control it, and what it doesn't do.
- 30 October 2026 · 7 min read
Claude Code memory: keep context between sessions (CLAUDE.md and MCP)
CLAUDE.md and auto memory keep a repository's context on your machine. To find it elsewhere, and in your other AIs, you need an MCP server.
- 30 October 2026 · 5 min read
Cursor: add a shared memory with a remote MCP server
One JSON block in mcp.json, one OAuth sign-in, one rule: Cursor's agent finds your projects' context and what you decided with your other AIs.
- 30 October 2026 · 5 min read
VS Code and Copilot: add a persistent memory with an MCP server
One command or a .vscode/mcp.json file, one sign-in in the browser: Copilot finds the context you built with Claude, ChatGPT or Cursor.
- 30 October 2026 · 4 min read
The 2-minute test: tell Claude, find it in ChatGPT
One fact told to Claude, a new chat in ChatGPT, and no repetition: if ChatGPT gets it right, your AIs really share the same memory.
- 30 October 2026 · 5 min read
What to store in your AI memory, and what never to put there
An AI memory is only as good as what goes in. Rule of thumb: keep what saves you from repeating yourself in three weeks, and nothing you wouldn't put in a shared notebook.
- 30 October 2026 · 5 min read
Import your ChatGPT memory into Pryzm (and share it with Claude)
ChatGPT already knows you. One message gets it to reread its memory and pour it into Pryzm, where all your connected AIs can use it.
- 30 October 2026 · 7 min read
Local vs hosted memory MCP server: which one to choose?
A local memory server keeps everything on your computer and only works there. A hosted one is an address every app can reach. What each gives you, what each costs you, and the options that exist.
- 30 October 2026 · 6 min read
Perplexity memory: what it remembers and how to extend it
Perplexity can remember your preferences and past searches. Where to control it, what its memory doesn't do, and how to give it a memory your other AIs share.
- 6 October 2026 · 9 min read
Hybrid search in Postgres: BM25, pgvector, RRF and a reranker
No separate search engine. One Postgres database, two rankings, one fusion and a reranker — with the parameters we actually run.
- 3 October 2026 · 6 min read
Encrypted AI memory: what the word actually covers
Every AI memory service says it is encrypted. The word covers four different guarantees, and only some of them protect you from the provider itself.
- 2 October 2026 · 6 min read
Connect ChatGPT to an external memory: the MCP server, step by step
A custom MCP server added as a plugin on chatgpt.com, one sign-in, then @ in the chat.
- 2 October 2026 · 6 min read
Claude MCP: add a custom connector (free plan included)
One URL in Customize → Connectors, one sign-in, and Claude can use an external tool. Even without a subscription.
- 1 October 2026 · 6 min read
Solo founder: switch from Claude to ChatGPT without re-explaining your project
When you build alone, your AIs are your team. They just need to remember the same things.
- 1 October 2026 · 6 min read
Freelancers: keep each client's preferences across missions and AIs
Five clients, three AIs, and the same question every time: which one didn't want informal copy again?
- 1 October 2026 · 6 min read
Team AI memory: no more “what did we decide again?”
In a small team, decisions are made everywhere and written down nowhere. And the AIs know nothing about them.
- 23 September 2026 · 6 min read
How to make ChatGPT remember your conversations
ChatGPT can remember you. It has to be switched on, you should know what it keeps, and it only helps if you never need those memories anywhere else.
- 23 September 2026 · 8 min read
The best memory MCP servers in 2026: 10 compared, local or hosted
There is no single best memory server. There is one for a memory that stays on your computer, one for self-hosting, one for agent builders, and one for a hosted memory you don't have to run.
- 23 September 2026 · 6 min read
How to transfer your ChatGPT memory to Claude
Switching assistants is easy. Taking your context with you is the part nobody documents. Three methods, from crude to durable.
- 22 September 2026 · 6 min read
How to give your AI assistants one shared memory
Every assistant now has its own memory, and none of them share it. A remote MCP server is the part that fixes that.
- 22 September 2026 · 7 min read
Where does your AI's memory actually live?
A memory layer is a database of everything you told an assistant. That makes it the most sensitive thing in your stack, and the least documented.
- 22 September 2026 · 6 min read
What is an MCP server, actually?
Strip the marketing away and MCP is a small, boring protocol. That is its best feature.
- 22 September 2026 · 8 min read
How persistent AI memory actually works
"The AI remembers me" is doing a lot of work as a sentence. Nothing in the model changed. Something in front of it got good at fetching.