{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihykwauqjt7g3ijxebaczun7ln5nkov67q3dsmpsgfjnnr5m4bnai",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mllrwlb66z62"
  },
  "path": "/t/features-request-memory-unification-between-codex-and-chatgpt/1380684#post_4",
  "publishedAt": "2026-05-11T17:12:42.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@teamlayer"
  ],
  "textContent": "Thanks for pointing me to the ‘Memory MCP’ thread previously shared by @teamlayer . It was an interesting idea and may partially solve the use case I mentioned here. Albeit a bit ‘hacky’.\n\nMy ask is for a native solution by OpenAI for Codex. Knowing what to keep in short (in session) and long (retrieval) is non trivial task and quite complex; attempted myself last winter with Google ADK ‘memory bank’ and compaction features.\n\nFast forward 6 months, with new techniques like ‘Skill’, I can see some of the memory management task can be offloaded to skill.md, particularly procedural ‘memory’. For semantic memory, potentially, can leverage the agent.md/LLM.md. But there still no solution for episodic memory. And if anything, that is what makes you, the user, ‘You’.",
  "title": "Features Request: Memory Unification between Codex and ChatGPT"
}