FIELD GUIDE

Share project memory between Codex and Claude Code

Use one reference for project decisions and current state without copying entire conversation histories.

Last reviewed:

About this guide

This guide was prepared with AI assistance using the project’s public documentation. It does not claim testing on every device or independent human review. Project publisher: AmirSina Zamanian.

Sources are listed at the end. Use the project repository to report an error or suggest a correction. Report an issue

On this page

What does shared memory mean?

Shared memory means both tools consult the same verified project state; it does not merge their internal model memory or chat history. In Personal Agentic OS, tool instruction files direct the agent toward the project context pack. That pack should retain the goal, decisions, open questions, and next action with provenance. Creating two instruction files alone does not demonstrate that either model has read them.
Source for this section

Start with one disposable project

Choose a non-sensitive project and a separate memory destination. Select only codex and claude during setup and review the proposed project map. When both candidates point to the same project path, inspect that they resolve to one canonical project. If paths differ, do not rely on similar names alone. In our published synthetic experiment, two candidates with the same path resolved to one project.
Source for this section

How do you hand over control?

In the first tool, review the accepted decision and next action with their source. After approved recording and sync, inspect that project’s context pack and remove unrelated or private material. In the second tool, explicitly request that it read the pack and restate the goal, decision, and open question before editing code. An incorrect restatement or missing source means the handoff is incomplete; do not approve changes yet.
Source for this section

What should you not assume?

This workflow is not a replacement for backups or access controls. A local file does not imply a local model: content supplied to a cloud-connected tool may be sent under that provider’s configuration. We claim neither token savings nor higher accuracy without a matched comparison. Use the installation guide and reproducible lab below for a safe first check.
Source for this section

Sources and next actions

Related guides

Was this guide helpful?

Your answer is recorded as an aggregate count to help choose and improve guides.