Does Claude Fable 5 have memory across chats?

Partly: the Claude app can carry some details between chats, but Claude Fable 5 itself is stateless and its memory never leaves the app. Here is an honest breakdown of what the new flagship remembers, where that stops, and how to give it persistent memory across every tool with Vilix.

Partly. If you use Claude Fable 5 through the Claude apps, Anthropic's app-level memory feature can carry some details from one chat into the next, and Projects let you pin files and instructions to a workspace. But that memory belongs to the app, not the model. Claude Fable 5 itself is stateless: every API call starts blank, every Claude Code session starts fresh, and nothing the Claude app remembers about you follows you to ChatGPT, Cursor, Codex, or any other tool. If you want memory that genuinely persists across chats, devices, and tools, you add it as a layer over MCP. This post covers both halves honestly: what the native memory does, and how to extend it.

What Claude Fable 5 remembers natively

Claude Fable 5 is Anthropic's new flagship model, a tier above Opus, with a 1 million token context window. Inside a single conversation that window is enormous: you can paste long documents and codebases and the model keeps track of all of it. Three native features add continuity around that window:

• In-chat context. Within one conversation, the app re-sends history on every turn, so the model appears to remember everything said so far, up to the context limit.
• App memory. The Claude apps can recall details from your past chats, depending on your plan and settings. You can review and edit what is stored.
• Projects. A Project groups chats, documents, and custom instructions, so every conversation inside it starts with the same shared context.

These are real and useful. The catch is where each one stops.

Where the native memory stops

The model itself has no memory between requests. A context window, even one of a million tokens, resets to zero the moment the conversation ends. The continuity you experience comes from the application layer re-sending history, which is why it does not travel:

• App memory lives in the Claude apps. It does not apply to API calls, and it does not load into Claude Code, Cursor, or any other tool where you also use Claude models.
• Claude Code sessions start cold. Per-repo CLAUDE.md files help, but you write and maintain them by hand, and they do not know what you discussed in the Claude app an hour ago.
• Nothing crosses providers. A decision you made with Claude Fable 5 is invisible to ChatGPT, Codex, or Grok, and vice versa.

So the precise answer to the headline question is: yes inside the Claude app, within Anthropic's limits, and no everywhere else. Every model launch repeats this pattern, because memory is an application problem, not a model problem.

How to give Claude Fable 5 persistent memory

The fix is to move memory out of any single app and into a layer that every tool can reach. Vilix is that layer, delivered as a single MCP connection. Two tools do all the work: before replying, the AI calls get_context with your latest message and Vilix returns your recent messages, saved memories, related past conversations, live project and task state, and your personal rules. After replying, it calls save_turn to persist the exchange. Because capture happens live on every turn, the memory is current, not a scraped profile that goes stale between syncs.

Connecting Claude on the web or desktop takes about a minute: open Settings, go to Connectors, add a custom connector, and paste the Vilix MCP URL:

https://api.vilix.ai/mcp

Approve the OAuth sign-in prompt in your browser and you are done. No API key, no config file. For Claude Code, add Vilix as an MCP server with one command:

claude mcp add --transport http vilix https://api.vilix.ai/mcp

The Vilix MCP docs cover the protocol details, and the MCP memory server setup guide for ChatGPT, Claude, and Cursor walks through the same connection in every major tool. Per-tool video walk-throughs live on the Get started page.

Same memory on your phone and your laptop

Because Vilix memory is stored server-side in your account rather than on a device, Claude Fable 5 on your phone and Claude Fable 5 on your laptop read from the same store. Start a conversation on mobile during a commute, open your laptop at your desk, and the next get_context call picks up exactly where you left off. The same applies across a reinstall or a new machine; there is nothing local to lose. How device continuity works in detail is covered in Same AI memory across devices.

Share context between Claude Fable 5 and ChatGPT, Cursor, or Codex

The bigger unlock is cross-tool. Vilix is a cross-AI memory layer: one account-level store that every connected tool reads from and writes to. Design an architecture with Claude Fable 5 in the Claude app, open Cursor, and the editor already knows the decisions you made. Draft a plan in ChatGPT and Claude Code sees it. Supported tools include ChatGPT, Claude, Claude Code, Cursor, Codex, Grok, Manus, GitHub Copilot, Windsurf, Lovable, OpenClaw, Hermes, and any tool that accepts a custom MCP connector. You connect each tool once, and the same memory, projects, tasks, and rules follow you everywhere.

Memory for always-on Claude Fable 5 agents

Agent operators feel the memory gap hardest. An always-on agent running on Claude Fable 5 through OpenClaw or Hermes loses its in-process state on every reboot, redeploy, or crash, and each channel it listens on arrives as a separate context. Wiring the same get_context and save_turn loop into the agent gives it durable, account-level memory that survives restarts and spans channels, with semantic search over everything it has ever discussed. The pattern is documented in how to add memory to any agent with Vilix MCP, with dedicated guides for OpenClaw and Hermes.

Getting started

Claude Fable 5 is the strongest model Anthropic has shipped, and it deserves better than starting every chat from zero. Connect Vilix once and it remembers across chats, across devices, and across every other AI tool you use. Try Vilix free (7-day full-Pro trial, no card required).

Frequently asked questions

Does Claude Fable 5 have memory across chats?

Only partly. The Claude apps can carry some remembered details between chats and Projects share context within a workspace, but the model itself is stateless. API calls and Claude Code sessions start blank, and nothing transfers to other tools. For memory that persists across every chat and tool, you add a memory layer such as Vilix over MCP.

How do I give Claude Fable 5 persistent memory?

Connect Vilix as a custom connector in the Claude app by pasting api.vilix.ai/mcp in Settings under Connectors, or run claude mcp add --transport http vilix https://api.vilix.ai/mcp for Claude Code. After the OAuth sign-in, the AI calls get_context before each reply and save_turn after it, so memory builds automatically on every turn.

Does Claude Fable 5 memory work across devices like phone and laptop?

Native app memory is tied to your Anthropic account and only works inside the Claude apps. With Vilix the memory is stored server-side in your Vilix account, so Claude Fable 5 on your phone and on your laptop load the same context, and a new device or reinstall loses nothing.

Can Claude Fable 5 share context with ChatGPT, Cursor, or Codex?

Not natively; Anthropic's memory never leaves the Claude apps. Through Vilix, yes: one MCP-connected memory store is shared by ChatGPT, Claude, Claude Code, Cursor, Codex, Grok, and any other tool that accepts a custom MCP connector, so context created in one tool is available in all of them.

Can always-on agents running Claude Fable 5 keep permanent memory?

Yes. Agents built on OpenClaw, Hermes, or a custom MCP-capable framework can call get_context before each action and save_turn after it. The memory lives in your Vilix account rather than in the agent process, so it survives reboots and redeploys and is shared across every channel the agent listens on.