Skip to content

Sync my chats, conversation history between ChatGPT website, Codex in VScode. #5609

Open
Open
Sync my chats, conversation history between ChatGPT website, Codex in VScode.#5609
Labels
enhancementNew feature or requestextensionIssues related to the VS Code extension

Description

@interconnectedMe
interconnectedMe
opened on Oct 24, 2025

What feature would you like to see?

I'd like to be able to see all my chats on whatever platform I am on, but specifically for me, when I am using:

  1. ChatGPT website
  2. ChatGPT website > Codex
  3. VScode, with Codex extension, on desktop
  4. e.g. GitHub Codespaces, on VScode, with Codex extension, on desktop (or Codespaces in browser with VScode)
  • So that any work done with chats on my local desktop, is then visible in e.g. Codespaces when I spin up (and vice versa).
  • Also so that while away from desktop / laptop, any ideas I may have that I throw in a chat on my phone, also show up.
  • ChatGPT Projects would be an obvious use case I can think of, to be able to load in VScode > Codex extension. That way, I can neatly drop any 'bright ideas' I may have, in a place that then makes sense.

At the moment, if I switch from VScode on desktop, to VScode (Codespaces), neither sees the other's chat history / tasks.

I have a janky workaround running that scans ~/.codex/sessions, then pulls each individual chat and formats to a .md file in a /worklog directory. So at least I can refer back to them (haven't yet tried the other way, to have these 'worklogs' pull in to my actual ChatGPT sessions history, but maybe that will work)

But it would be a very nice feature, I think, if ChatGPT 'just remembered' our history, wherever I was.

Additional information

No response

Activity

  1. interconnectedMe
    added
    enhancementNew feature or request
    on Oct 24, 2025
  2. github-actions
    added
    extensionIssues related to the VS Code extension
    on Oct 24, 2025

  3. github-actions commented on Oct 24, 2025

    @github-actions
    github-actionsBot
    on Oct 24, 2025 – with GitHub Actions
    Contributor

    Potential duplicates detected. Please review them and close your issue if it is a duplicate.

    Powered by Codex Action

  4. etraut-openai commented on Nov 15, 2025

    @etraut-openai
    etraut-openai
    on Nov 15, 2025
    Contributor

    This is related to #2153

  5. crsmoore commented on Apr 18, 2026

    @crsmoore
    crsmoore
    on Apr 18, 2026

    I too would like to see more "unification" of things.

    I really want a "superapp" that just has everything, on both macOS and iOS (or Windows/Android, etc.)

    This would lead to less fragmentation, more shared context, and seamless workflows.

  6. Vishnu0007-svj commented on Jul 11, 2026

    @Vishnu0007-svj
    Vishnu0007-svj
    on Jul 11, 2026

    So have you come to any solution yet or still into that janky workaround??

  7. Lawouach commented on Jul 16, 2026

    @Lawouach
    Lawouach
    on Jul 16, 2026

    It is impressive that this isn't native yet. Creating your own fragmentation is a choice.

  8. noyanxtdoor-maker commented on Aug 10, 2026

    @noyanxtdoor-maker
    noyanxtdoor-maker
    on Aug 10, 2026 – with ChatGPT Codex Connector

    I strongly support this request, but I’d like to add one important extension: true two-way sync between a ChatGPT conversation and a Codex task, not just shared chat history.

    My normal workflow is:

    ChatGPT planning / architecture → Codex implementation → ChatGPT review → Codex revision

    Today, that loop requires a lot of manual context transfer. The ideal workflow would be:

    1. From a ChatGPT thread, choose Send to Codex / Implement with Codex.
    2. Codex receives the relevant approved plan, architecture, requirements, attachments, and project context from that thread.
    3. The ChatGPT thread and Codex task become persistently linked.
    4. While Codex is working, meaningful progress/status updates flow back into the originating ChatGPT thread (what it is implementing, files being changed, tests, blockers, important decisions).
    5. When Codex finishes, the same ChatGPT thread automatically receives the implementation summary, changed files/diffs, test results, unresolved issues, commit info, and PR link when applicable.
    6. ChatGPT can review those results using the original planning context, and follow-up instructions can be sent directly back to the same Codex task.
    7. That loop can continue without repeatedly copying context back and forth.

    So the model I’m asking for is essentially:

    ChatGPT plan → Codex execute → Codex progress/results → ChatGPT review → Codex revise → repeat

    For larger projects, ChatGPT works extremely well as the planning, architecture, product-design, and review layer, while Codex is the execution layer. Connecting those two layers with persistent two-way project context would remove a major source of friction.

    A shared Project Context or linked ChatGPT/Codex session could be one way to implement it, while still keeping discussion and code execution clearly separated.

    OpenAI Support specifically directed me to this GitHub tracker for Codex feature requests, so I’m adding this here rather than relying on the support thread alone.

  9. harahihara commented on Aug 14, 2026

    @harahihara
    harahihara
    on Aug 14, 2026 – with ChatGPT Codex Connector

    I’d also like to request first-class synchronization and remote access specifically between the Codex desktop apps on macOS and Windows.

    Desired workflow:

    • Sign in with the same OpenAI account on a Mac and a Windows PC.
    • See the same Codex projects, threads, chat history, titles, pins, and relevant task state on both computers.
    • Continue a thread on either computer without manually copying ~/.codex/sessions or exporting summaries.
    • Securely connect to and control Codex running on the other computer in either direction (Mac → Windows and Windows → Mac), including reviewing progress, answering questions, approving actions, and steering active tasks.
    • Clearly distinguish cloud-synced metadata/history from machine-local files, credentials, permissions, terminals, and execution state.

    For safety and reliability, an optional sync model with encryption, device management/revocation, explicit local-only threads, conflict handling, and clear offline behavior would be valuable. Synchronizing the live .codex directory through OneDrive/iCloud is unsafe because SQLite/session files can conflict, so an official solution would address an important cross-device workflow gap.

  10. XxUnkn0wnxX commented on Aug 22, 2026

    @XxUnkn0wnxX
    XxUnkn0wnxX
    on Aug 22, 2026

    For anyone whose immediate need is read-only access to existing ChatGPT conversations from Codex, there is a useful unofficial workaround available now: shoyu-ramen/codex-chats-mcp.

    It exposes ChatGPT conversations through a local STDIO MCP server, including list, search, and get operations. This is not a replacement for the broader native feature requested here: it does not synchronize local ~/.codex/sessions across machines, provide live two-way ChatGPT ↔ Codex task sync, or unify execution state. It is mainly useful for finding and reading prior ChatGPT conversations from Codex.

    One important installation caveat as of codex-chats-mcp 0.1.1: its dependency is currently declared as mcp[cli]>=1.0, so a fresh install can resolve MCP Python SDK 2.0.0. The server still imports the v1-only mcp.server.fastmcp API and will then exit during startup with:

    ModuleNotFoundError: No module named 'mcp.server.fastmcp'

    Until the package pins v1 or migrates to the MCP SDK 2.x APIs, the verified workaround is to pin MCP SDK 1.29.0 inside the package's dedicated virtual environment:

    /path/to/venv/bin/python -m pip install "mcp[cli]==1.29.0"
/path/to/venv/bin/python -m pip check

    With Python 3.13.9, I verified that this restores the FastMCP import and allows an independent MCP initialize() and list_tools() handshake to complete successfully. Details and the upstream fix/migration proposal are tracked here: shoyu-ramen/codex-chats-mcp#1 (comment)

    The server also offers rename/archive/delete operations, so anyone wanting a read-only setup should restrict the Codex MCP entry explicitly:

    enabled_tools = [
    "list_conversations",
    "search_conversations",
    "get_conversation",
]

  11. XxUnkn0wnxX commented on Sep 19, 2026

    @XxUnkn0wnxX
    XxUnkn0wnxX
    on Sep 19, 2026

    Quick update to my earlier comment: I've forked and migrated the server to the MCP Python SDK 2.x and published codex-chats-mcp-v2 0.2.0 for people to try/test.

    A fresh PyPI install has been verified with MCP SDK 2.2.0, and Linux/macOS/Windows CI is passing. The MCP v1 pin in my previous comment is not needed for this fork.

    Install inside a fresh virtual environment:

    python -m pip install "codex-chats-mcp-v2==0.2.0"

    Don't install it alongside the upstream codex-chats-mcp package in the same environment: both provide the same module and codex-chats-mcp executable. The README covers MCP configuration and source installs.

    For read-only testing, keep the list_conversations, search_conversations, and get_conversation allowlist from my earlier comment; the server also exposes write/delete tools.

    The fork adds bounded retries for transient Cloudflare HTML failures on read requests, but it is not a Cloudflare bypass. It still uses undocumented ChatGPT endpoints and existing Codex sign-in credentials.

    This remains an unofficial way to access existing chats, not native cross-device session sync or live two-way ChatGPT/Codex task synchronization.

    Feedback/testing would be welcome. Please report problems in the fork's issue tracker, with OS/MCP versions and sanitized errors—not credentials or conversation content.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or requestextensionIssues related to the VS Code extension

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions