Your AI coding agent has been working with you for hours, maybe days. It knows why the code looks the way it does. It knows what you tried yesterday, what failed, which ugly workaround is intentional, and what you were planning to do next.
You still have another agent available. Maybe it runs through OpenRouter. Maybe it is local. Maybe you have credits somewhere else. Maybe you simply want to switch models.
The problem is not finding another AI. The problem is that the new AI just arrived.
Your repository contains the code, but not necessarily the story behind the code.
So before the next agent can continue the work, we need to move that story somewhere both agents can reach.
I: Create a Room Create an empty Living Memory Room for the project. At first, it knows nothing. That is intentional. Think of it as a shared workspace that different agents can enter.
II: Move the current work context into the Room Before your current agent disappears, ask it to leave behind what the next agent needs: what you are building the current state important decisions what it already tried what failed what is unfinished what should happen next Then have it leave a handoff.
III: Connect another agent Connect whichever agent you want to use next to the same Room. Tell it to read the handoff first, then inspect the actual repository.
Now it has two things: the Room tells it what happened; the repository tells it what exists.
IV: Before that agent leaves, update the Room again When it finishes its turn—or starts running low on tokens—have it update the important state and leave another handoff.
Creating a Room does not magically recover your previous Claude Code, Codex, ChatGPT, or other agent sessions. If you have already been working on a project for three days and create a Room today, those three days do not suddenly appear inside it. You have to migrate the useful context once. Fortunately, you probably already have something that knows most of it.
Connect the agent that has been working on the project to the new Room. Ask it to inspect the project and record the durable things the next agent should know.
We may need to continue this project with another agent later. Review our current work and the repository. Save the important durable context to this Room: the goal, architecture or constraints that matter, decisions we made and why, important failed attempts, current state, and anything a future agent should know.
Then leave a handoff describing exactly where the work is now and what should happen next.
This is the annoying case. Maybe you already hit the limit. Maybe the session disappeared. Maybe that particular model is unavailable.
You can still bootstrap the Room. Use an AI that already knows the project well.
For example: I often discuss my work with ChatGPT separately from the coding agent actually editing the repository. That conversation may already contain the goals, decisions, problems, and current direction of the project.
I can ask it to reconstruct the useful context and put that into the Room first.