{"slug": "give-claude-code-cursor-and-chatgpt-one-shared-memory", "title": "Give Claude Code, Cursor and ChatGPT one shared memory", "summary": "OwlMem, a product from the team behind owlmem.com, launched a shared memory service that connects Claude Code, Cursor, ChatGPT, Codex and other AI tools through a single MCP server endpoint. The installer (npx -y owlmem install) detects installed AI apps and merges OwlMem into their existing config files with backups, while manual setup uses commands like 'claude mcp add --transport http --scope user owlmem https://mcp.owlmem.com/mcp' or a URL entry in Cursor's mcp.json. The service is free for two connected AIs, with paid tiers adding more agents, storage and memory writes.", "body_md": "If you use more than one AI, you know the tax: every new tool starts from zero. You explain the project, your preferences, your rules — again. Switch tools mid-job and the next AI has no idea where the last one stopped.\n\nOwlMem fixes that with one shared memory. (Disclosure: OwlMem is our own product — [owlmem.com](https://owlmem.com/?utm_source=dev.to&utm_medium=article&utm_campaign=growth-2026-11).) Tell one AI something once, and every connected AI can recall it. What one learns, they all know.\n\nEvery client connects to the same MCP server:\n\n```\nhttps://mcp.owlmem.com/mcp\n```\n\nThe fastest way is to let your AI do it. In Claude Code, Codex, Cursor, or any AI that can run commands, say:\n\n```\nRead https://mcp.owlmem.com and set up OwlMem for yourself.\n```\n\nIt reads the setup guide, runs the installer, and asks you to sign in. All you do is click **Allow**. Or run the installer yourself:\n\n```\nnpx -y owlmem install\n```\n\nIt finds the AI apps on your computer and adds OwlMem to each one, merging into your existing config files instead of overwriting them, and backing up anything it changes. I ran it in dry-run mode to see what it would do on a machine with Codex installed:\n\n```\nOwlMem install — connects the AI apps on this computer to https://mcp.owlmem.com/mcp (dry run, nothing is changed)\n\n– Claude Code       not installed\n+ Codex             will add OwlMem  (~/.codex/config.toml)\n    will write the OwlMem rules block in ~/.codex/AGENTS.md\n– Cursor            not installed\n– VS Code           not installed\n– Windsurf          not installed\n– Gemini CLI        not installed\n– Claude Desktop    not installed\n\nDry run: 1 app(s) would change. Run again without --dry-run to apply.\n```\n\nIf you'd rather add each one by hand, the commands are short:\n\n**Claude Code:**\n\n```\nclaude mcp add --transport http --scope user owlmem https://mcp.owlmem.com/mcp\n```\n\nThen start Claude Code, type `/mcp`, select `owlmem`, and choose **Authenticate**.\n\n**Cursor:** add the URL to `~/.cursor/mcp.json`, then open Cursor Settings → MCP. OwlMem shows **Needs login** — click it and approve in the browser.\n\n```\n{\n  \"mcpServers\": {\n    \"owlmem\": { \"url\": \"https://mcp.owlmem.com/mcp\" }\n  }\n}\n```\n\n**ChatGPT:** open Settings → Apps & Connectors, turn on **Developer mode** under Advanced settings, choose **Create**, name it `OwlMem`, paste the URL, and choose **OAuth**. One caveat from the docs: availability of custom connectors depends on your ChatGPT plan and workspace settings — if you don't see the option, your plan may not include it.\n\n**Codex:**\n\n```\ncodex mcp add owlmem --url https://mcp.owlmem.com/mcp\n```\n\nWhichever way you connect, the first connection opens an OwlMem page: sign in with your email, name the AI, click **Allow**. No keys to copy. Every connected AI shows up in the console under **Agents & tools → Agents**, where you can switch it off or delete it any time.\n\nOnce two AIs are connected, the test takes thirty seconds:\n\nChatGPT answers from what Claude recorded — no copy-pasting context between apps. That's the whole point: the memory lives in one place you control, not inside any single AI's chat history. Switch tools whenever you like and keep it all.\n\nFree for two AIs, forever — no card. That covers the exact setup above: one coding AI and one chat AI sharing a memory. Paid plans add more AIs, storage, and memory writes; every plan gets every feature.\n\nIf you already juggle Claude Code, Cursor, and ChatGPT, the shared memory is the part you'll feel first: you stop paying the re-explaining tax on every switch. Set it up from the [docs](https://owlmem.com/docs?utm_source=dev.to&utm_medium=article&utm_campaign=growth-2026-11) — about a minute per AI.", "url": "https://wpnews.pro/news/give-claude-code-cursor-and-chatgpt-one-shared-memory", "canonical_source": "https://dev.to/owlmem/give-claude-code-cursor-and-chatgpt-one-shared-memory-4po9", "published_at": "2026-11-20 04:09:18+00:00", "updated_at": "2026-11-20 04:13:13.543562+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "developer-tools", "ai-products"], "entities": ["OwlMem", "Claude Code", "Cursor", "ChatGPT", "Codex", "VS Code", "Windsurf", "Gemini CLI"], "also_reported_by": [], "takeaway": "A single MCP server URL (https://mcp.owlmem.com/mcp) can be registered across Claude Code, Cursor, Codex and ChatGPT so memory written by one agent is recalled by the others.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/give-claude-code-cursor-and-chatgpt-one-shared-memory", "markdown": "https://wpnews.pro/news/give-claude-code-cursor-and-chatgpt-one-shared-memory.md", "text": "https://wpnews.pro/news/give-claude-code-cursor-and-chatgpt-one-shared-memory.txt", "jsonld": "https://wpnews.pro/news/give-claude-code-cursor-and-chatgpt-one-shared-memory.jsonld"}}