AI memory for teams

A memory for Gemini CLI your team shares.

GEMINI.md remembers one project. Contexel remembers what your team decided everywhere else, and Gemini CLI can look it up.

Why Gemini CLI needs a shared memory

A GEMINI.md file is great for one project. It can't hold what was decided in another repository, in a chat, or by a teammate using a different app.

  • Beyond one project.Conventions and decisions follow you into every folder you work in.
  • Beyond one app.What you saved from Claude, ChatGPT or Cursor is there in your terminal.
  • Beyond one person.Your teammates' AI reads the same shared memory, and every answer names its source.

Connect Gemini CLI in about a minute

  1. Sign in to Contexel. It takes about a minute.
  2. Add Contexel to your Gemini CLI settings file, ~/.gemini/settings.json: "mcpServers": { "contexel": { "httpUrl": "https://contexel.ai/mcp" } }
  3. Start Gemini CLI and sign in with your browser when it asks. If it doesn't ask, run /mcp auth contexel.
  4. Ask Gemini CLI to remember something.

Then just talk to it

There's nothing new to learn. Ask your AI to remember something, and ask about it later from any connected app.

You, in ChatGPTRemember for the team: staging resets every Sunday night, so don't leave test data there.

Later, a teammate in Gemini CLICan I leave these test accounts on staging over the weekend?

Questions

Should I stop using GEMINI.md?

No. Keep it for instructions about one project. Use Contexel for what your team knows across projects and apps.

Does my code get uploaded?

No. Contexel only stores what you or your AI choose to save as a memory. It does not read your files.

Who can see what I save?

You start with a private workspace that only you can use. You choose when to create a shared one and who to invite.

Using other AI apps too?

It's the same memory everywhere. Connect as many apps as you like.

Stop repeating yourself to Gemini CLI.

Connected in about a minute.