# Make Ditto Part of Your AI Workflow > Teach Claude, Codex, Cursor, Gemini CLI, Copilot, or ChatGPT when to recall and save Ditto memories across your daily work. --- Connecting the [Ditto MCP server](/docs/mcp-server) gives an assistant memory tools. A persistent instruction tells it when to recall context and save a useful checkpoint, so you do not have to mention Ditto in every prompt. ## Copy This Instruction Add this block to your assistant's persistent or project instructions: ```text Use Ditto as my long-term memory when it is relevant, not on every turn. - Before substantive work involving my projects, people, preferences, decisions, or commitments, search Ditto for relevant context and the latest checkpoint. Fetch the full memories you rely on. - Save only durable outcomes: confirmed decisions, meaningful milestones, changed project state, resolved blockers, commitments, stable preferences, corrections, and the next useful step. - Save the outcome, not a transcript. Skip drafts, raw logs, temporary values, facts already clear from project files, secrets, and credentials. - Avoid duplicates. Update an existing memory when it has changed instead of creating a competing version. - Never publish, share, or delete a memory unless I explicitly ask. Briefly tell me what you saved or updated. ``` If you prefer review before every write, append: `Before calling save_memory or update_memory, show me the proposed memory and wait for approval.` ## Set Up Your Assistant First [connect Ditto](/docs/mcp-server) at `https://api.heyditto.ai/mcp`, then paste the instruction above into the location for your assistant: | Assistant | Persistent instruction | Connect Ditto | | -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Claude.ai / Claude Desktop | Settings → Instructions for Claude, or project instructions ([guide](https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features)) | Customize → Connectors → Add custom connector ([guide](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp)) | | Claude Code | `~/.claude/CLAUDE.md` or project `CLAUDE.md` ([guide](https://code.claude.com/docs/en/memory)) | `claude mcp add --transport http --scope user ditto https://api.heyditto.ai/mcp` ([guide](https://code.claude.com/docs/en/mcp)) | | OpenAI Codex | `~/.codex/AGENTS.md` or project `AGENTS.md` ([guide](https://learn.chatgpt.com/docs/agent-configuration/agents-md)) | `codex mcp add ditto --url https://api.heyditto.ai/mcp`, then `codex mcp login ditto` ([guide](https://learn.chatgpt.com/docs/extend/mcp?surface=cli)) | | Cursor | Settings → Rules → User Rules, or `.cursor/rules/*.mdc` ([guide](https://docs.cursor.com/context/rules-for-ai)) | Settings → MCP → add a remote server ([guide](https://docs.cursor.com/context/model-context-protocol)) | | Gemini CLI | `~/.gemini/GEMINI.md` or project `GEMINI.md` ([guide](https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/gemini-md.md)) | `gemini mcp add --scope user --transport http ditto https://api.heyditto.ai/mcp` ([guide](https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md)) | | GitHub Copilot in VS Code | `~/.copilot/copilot-instructions.md`, `.github/copilot-instructions.md`, or `AGENTS.md` ([guide](https://code.visualstudio.com/docs/agent-customization/custom-instructions)) | Command Palette → MCP: Add Server ([guide](https://code.visualstudio.com/docs/agent-customization/mcp-servers)) | | ChatGPT (plan-limited) | Settings → Personalization → Custom Instructions ([guide](https://help.openai.com/en/articles/8096356-custom-instructions-for-chatgpt)) | Developer mode → add a custom MCP app ([limits](#chatgpt-plan-limited)) | Complete Ditto OAuth when prompted. Use a global instruction for all work and a project instruction when the memory workflow should stay scoped to one project. ### ChatGPT (plan-limited) Custom MCP availability differs by plan: Check whether your plan and workspace allow custom MCP apps and write tools. If your connection exposes only read/fetch tools, use it for recall; saving checkpoints requires a client with memory-write tools enabled. See OpenAI's [Developer mode and MCP apps](https://help.openai.com/en/articles/12584461-developer-mode-and-mcp-apps-in-chatgpt) documentation for current availability. ## What Good Use Looks Like 1. **Start with context.** On substantive work, the assistant searches for the project's latest checkpoint, decisions, and your established preferences before planning. 2. **Save at real milestones.** It records decisions, resolved blockers, handoffs, or end-of-session state—not every command or aside. 3. **Resume cleanly.** A later assistant can retrieve the saved state, fetch the full memory behind the relevant result, and continue with less re-explaining. ## Privacy and Control - Ditto sends memory content only when the assistant calls a read tool. Returned content is then handled under that provider's data policies. - Memory writes are real actions. Use a read-only key or require approval before `save_memory` and `update_memory` if you want tighter control. - Saving is private by default. Publishing, sharing, and deletion are separate actions. - Prefer OAuth. If you use API keys, create one per client at [assistant.heyditto.ai/mcp](https://assistant.heyditto.ai/mcp), and never place it in an instruction file or repository. If Ditto is never used, confirm the server and instruction are enabled, then ask once: `Search Ditto for the latest checkpoint on …`