← All guides
Continuity · Zambo

Cross-AI continuity — your AI is replaceable. Your work isn't.

Cross-AI continuity means starting a job in one AI, continuing it in a different AI, and verifying it in a third. The models do not share a chat history. They share only the stable session ID, the user's instructions, and the receipts returned by Zambo.

How it works

Call zambo_universal with the user's exact request and one stable session_id. When the work is unfinished, call the same tool with mode: "continue" and that same session ID. Before declaring the job complete, use mode: "verify". Each execution returns a receipt with the observed UUID, timestamp, and hash so another AI can quote the evidence instead of guessing what happened.

One MCP connection
{"mcpServers":{"zambo":{"url":"https://zambo.dev/api/mcp"}}}
https://zambo.dev/api/mcp

Worked example

  1. Claude: call zambo_universal with need and session_id to start the research job.
  2. ChatGPT: receive that session ID from the user and call zambo_universal with mode: "continue" to perform the next step.
  3. Cursor: call zambo_universal with mode: "verify", then present the receipt and distinguish completed, blocked, and suggested work.

FAQ

Does the second AI need my chat history?

No. It needs the stable session ID and the next instruction.

How is this different from AI memory?

Memory is one model's recall. Continuity is portable work state and proof across models.

Is it free?

Yes, within the free tier's published call limits: no account is required.

Build an agent workflow →