DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to continue long ChatGPT tasks in a fresh conversation with Openchatx MCP

Hand off a long-running task to a new chat using a stored summary and a UUID.

Who it is forA person working on a multi-day task in ChatGPT who has hit the practical context limit of one conversation.

The problemWhen a chat gets too long, the work state is lost unless you rebuild the context by hand.

The outcomeA new ChatGPT conversation receives the stored summary and recent context from the old one, and the agent resumes the task.

What you need first

  • A ChatGPT account with access to Developer Mode and MCP apps, or the Plugins flow described in the README
  • An OpenAI Platform account with permission to create a Secure MCP Tunnel and a Runtime API key
  • Windows or macOS for the Desktop App, or Node.js 22.18+, npm, ripgrep, and OpenAI tunnel-client for the source install

Steps

  1. Complete the Connect OpenChatX to ChatGPT setup so the MCP connection works.
  2. In the old chat, ask the Agent to call summarize and save the returned UUID.
  3. Start a fresh ChatGPT conversation.
  4. Give the Agent the UUID and ask it to call summarize with that UUID.
  5. Check the Dashboard Summaries view to confirm the temporary summary exists before you delete it.

Prompt for your agent

Using the openchatx-mcp repo, call summarize at the end of the current task and return the UUID. In a new chat, call summarize with the UUID <uuid> and continue the task at <next-step>. Verify that the reply names the last completed step from the stored summary.

Caveat. The handoff is deleted automatically after it is used, so save any important detail elsewhere before you start the new chat.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page