MnemoverseDocs

Appearance

ChatGPT: Custom GPT Actions ​

For new everyday use, install the published Mnemoverse Memory plugin. This page preserves the separate REST/API-key integration for maintaining a Custom GPT or an account that still offers its creation. GPT Actions are not the MCP tools provided by the published plugin.

Historical platform status, checked 1–21 October 2026: OpenAI's creation guide then described GPT creation in Business, Enterprise and Edu workspaces. Its retirement FAQ named 11 December 2026 for retirement, with exceptions, and said custom actions would not transfer through migration. Check those sources and your account before investing in a new Actions setup. These dated constraints do not describe the published Mnemoverse plugin.

How It Works ​

You → ChatGPT → GPT Action (HTTP) → core.mnemoverse.com
                     │
              X-Api-Key: mk_live_xxx

ChatGPT calls the Mnemoverse API directly through GPT Actions. No middleware, no proxy. Your GPT stores and recalls memories using the same API key as your other tools.

Setup (5 minutes) ​

Step 1. Get Your API Key ​

Sign up at console.mnemoverse.com and create a free API key. It starts with mk_live_.

Create the key in the same Mnemoverse account as your other tools to share their memories. Enter it only in the GPT builder's authentication field, never in a chat.

Step 2. Create a Custom GPT ​

The steps below preserve the procedure checked on 1 October 2026. Confirm that your account still offers the GPT builder; use the published plugin for ordinary setup.

  1. In an account or workspace that offers GPT creation, open Explore GPTs, or go to chatgpt.com/gpts.
  2. Select Create to open the GPT builder, and choose the configuration view to edit its fields directly.

These two steps follow OpenAI's Creating and editing GPTs, read 2026-10-01.

Step 3. Configure Actions ​

  1. Scroll down to Actions → Create new action
  2. Set Authentication:
    • Type: API Key
    • API Key: paste your mk_live_YOUR_KEY
    • Auth Type: Custom
    • Custom Header Name: X-Api-Key
  3. In the Schema box, click Import from URL and paste:
https://mnemoverse.com/docs/openapi-gpt.yaml

You should see 4 actions appear: writeMemory, readMemory, giveFeedback, getMemoryStats.

Step 4. Set the System Prompt ​

Paste this into the Instructions field (customize to your needs):

You have persistent long-term memory via Mnemoverse.

RULES:
1. BEFORE answering any question about preferences, past decisions, project
   setup, people, or anything that might have been discussed before — call
   readMemory first.
2. When the user asks you to save information, or has enabled an agreed memory
   workflow, call writeMemory for useful durable facts. Check the result before
   saying it was saved; do not store secrets or unrelated details.
3. After using memories to answer a question, call giveFeedback to report
   whether they were helpful (1.0) or not (-1.0).
4. Your memory persists across sessions and across tools. What you learn here
   is available in Claude Code, Cursor, and everywhere else.

WHAT TO REMEMBER:
- Preferences ("I prefer Railway over Heroku")
- Decisions ("We chose PostgreSQL for this project")
- Lessons ("Exponential backoff fixed the timeout issue")
- People ("Alice owns the design system")
- Project context ("Deploy target is staging.example.com")

WHAT NOT TO REMEMBER:
- Trivial small talk
- Temporary context ("open this file")
- Information already in the current conversation

Step 5. Test It ​

Say to your GPT:

"Remember that I always deploy to Railway using railway up"

Check that writeMemory succeeded. Then start a new conversation and ask:

"How do I deploy?"

Check that readMemory returns the saved fact. A natural-language claim without the action result does not verify persistence.

Available Actions ​

Your GPT gets 4 actions:

ActionWhat it does
writeMemoryStore a preference, decision, or lesson
readMemorySearch memories by natural language query
giveFeedbackReport if a memory was helpful (+1) or wrong (-1)
getMemoryStatsCheck how many memories are stored

These are the same operations available in Claude Code, Cursor, and the Python SDK — just exposed through GPT Actions.

Tips ​

Choose a memory workflow. Agree with the user what to save automatically. Otherwise, save when asked and check the write result.

Use domains. If your GPT serves a specific project, add "domain": "project:acme" to writes and reads. This keeps memories organized.

Feedback matters. The giveFeedback action rates the memories a search returned: rating a recalled memory as helpful or misleading re-ranks what comes back next. Nothing is erased.

Limitations ​

  • GPT Actions time out after 45 seconds round trip (Production notes on GPT Actions, read 2026-10-01).
  • ChatGPT may not call actions on every turn; the instructions from Step 4 guide it. Actions do not run in Pro mode: for a GPT with actions, ChatGPT offers only models that support them (Configuring actions in GPTs, read 2026-10-01).
  • Rate limits apply per organization, not per API key: all keys belonging to your organization share the same limits. Free tier: 1,000 queries/day. Upgrade for more.

OpenAPI Spec ​

The full spec is at /openapi-gpt.yaml. It defines 4 endpoints:

  • POST /memory/write — store a memory
  • POST /memory/read — search memories
  • POST /memory/feedback — rate usefulness
  • GET /memory/stats — memory statistics

This is a curated subset of the full API. For batch operations and advanced queries, use the REST API or Python SDK directly. Consolidation is not one of them: it is off on the hosted service, and POST /memory/consolidate answers 503 with a typed reason.