--- title: "Memory.Wiki FAQ" url: https://memory.wiki/mdfy-faq updated: 2026-05-24T17:46:16.671Z hub: https://memory.wiki/hub/raymindai bundle_count: 1 concept_count: 12 source: "mdfy-content" --- # Memory.Wiki FAQ ## How is Memory.Wiki different from Notion / Obsidian? Notion and Obsidian are great as personal knowledge bases for *humans*. Memory.Wiki is built so the *AI* can read it. The output is a public URL whose markdown is what every LLM already knows how to consume. No plugin, no SDK, no shared workspace. You can absolutely use Notion *and* Memory.Wiki. Many people do: Notion for active editing, Memory.Wiki for the "publish so any AI can read it" moment. ## Do I need an account? No. You can capture and share without signing up. Anonymous captures get a cookie that groups them, and you can sign in later to claim them all into your hub. ## How does Memory.Wiki compare to mem0 / OpenMemory / Letta? Those are backend memory layers for AI agents. They expose an API or MCP server, store atomic memories, and inject context automatically into one tool. Memory.Wiki is a publishing layer: human-shaped content at a public URL that any AI can read across tools. They solve different problems, and you can use both. See [How Memory.Wiki Memory works](/mw-memory) for the technical comparison and [MWBench](/mwbench) for the cross-AI verification. ## Does Memory.Wiki work without paying anything? Free during beta. After beta, a Pro tier is planned with no functional removals. Pro adds features (Pro hub layout, custom domain, analytics). Document expiry is **never** a tier feature; every URL is permanent regardless of plan. ## Can I edit my docs after publishing? Yes. If you're signed in, every doc you own is editable from the main editor at `memory.wiki/`. If you captured anonymously, you got an `editToken` (stored locally) that lets you edit without signing in. Sign in later and your docs migrate into your account. ## Can other people edit my docs? Per-doc share modes: - **Owner only** (default). - **Anyone with link** (read). - **Specific people** (read or edit, by email allow-list). - **Public** (anyone can edit, for collaborative wikis). ## What happens to my docs if Memory.Wiki goes away? The engine is open source on GitHub. The Bundle Spec is a stable contract. Worst case, you export everything as raw markdown and stand it up elsewhere. The URL is the contract, and markdown is portable. ## Is the AI memory thing actually useful? Honest answer: **only if you use multiple AI tools daily.** If you're a one-vendor user (only ChatGPT, only Claude), that vendor's built-in memory is probably enough. Memory.Wiki starts paying off once you regularly switch between Claude / ChatGPT / Cursor / Codex and want the answer from one tool to inform the next. ## Where does the name come from? Memory + Wiki. Your memory, as a wiki, at a URL. Pronounced however you like. --- ## Summary Memory.Wiki is a publishing platform designed so AI systems can read human knowledge bases as public markdown URLs, functioning as a memory layer across multiple AI tools rather than within a single vendor's ecosystem. It differs from personal knowledge bases like Notion by prioritizing AI readability, and from agent memory systems like mem0 by operating as a publishing layer rather than a backend API. ## Themes - AI-readable publishing layer - Cross-tool memory portability - Human-first content design ## Key takeaways - Memory.Wiki is built for AI consumption as a public markdown URL, unlike Notion and Obsidian which are designed for human personal knowledge management - Users can capture and share anonymously with cookies, then claim content into an account later by signing in - Per-document sharing modes include owner-only, anyone-with-link read-only, specific-people with email allowlisting, and public collaborative editing - The open source engine and stable Bundle Spec ensure content portability: users can export as markdown and host elsewhere if Memory.Wiki discontinues - Memory.Wiki primarily benefits users who work across multiple AI tools daily, not single-vendor users relying on built-in memory features ## Insights - Memory.Wiki positions itself as complementary to both personal knowledge tools (Notion/Obsidian) and AI backend memory systems (mem0/Letta), not as a replacement for either - The business model defers monetization of core functionality, committing that document permanence and accessibility will never become a paid feature - The honest acknowledgment that the product's value proposition only materializes for users with multi-vendor AI workflows suggests a specific target persona rather than universal appeal ## Open questions / gaps - What is the specific technical mechanism by which Memory.Wiki ensures LLMs across different platforms can access and update the same content reliably? - What does the Pro tier's custom domain and analytics features enable that free tier users cannot do? ## Concepts in this document - **memory.wiki** _(entity)_ The primary product platform being developed and documented. - **Knowledge Management** _(tag)_ Overarching domain of personal and organizational information systems - **Claude** _(entity)_ Specified AI tool for prototyping and validation before moving to high-fidelity design. - **ChatGPT** _(entity)_ One of the AI platforms currently suffering from isolated memory silos. - **Cursor** _(entity)_ One of the AI platforms currently suffering from isolated memory silos. - **Obsidian** _(entity)_ Competitor noted as a note-taking tool in relation to memory concepts. - **Mem0** _(entity)_ Competitive reference mentioned in the redefinition document. - **Semantic search** _(concept)_ 300ms-debounced backend search alongside title-match, enabling meaning-based discovery of documents. - **Developer Tools** _(tag)_ Technical tooling aspect including CLI, SDK, and MCP integrations for power users. - **AI Integration** _(tag)_ Technical capability to work seamlessly with multiple AI platforms - **Auto-synthesis** _(tag)_ Automated content organization and insight generation using LLM analysis of document collections. - **Bundle Spec v1.0** _(entity)_ Standardized specification ensuring bundles have stable, parseable structure for future tool compatibility. ## Concept relations (within this doc's concepts) - **Cursor** categorized as **Developer Tools** - **memory.wiki** targets platform **Claude** - **memory.wiki** targets platform **ChatGPT** - **memory.wiki** targets platform **Cursor** - **Cursor** saves decisions to **memory.wiki** - **Claude** loads context from **memory.wiki** - **Bundle Spec v1.0** defines format for **memory.wiki** - **memory.wiki** complements **Obsidian** - **Auto-synthesis** automation approach **Knowledge Management** - **memory.wiki** lacks implementation of **Semantic search** - **AI Integration** targets **Claude** - **AI Integration** targets **ChatGPT** - **AI Integration** targets **Cursor** - **memory.wiki** developed with **Claude** ## Bundles containing this document - [Memory.Wiki Foundations](https://memory.wiki/b/9FATHAnw) > What Memory.Wiki is, the three URL primitives, the memory architecture, the /memory.wiki skill across coding tools, the Bundle Spec, FAQ, and roadmap. Read in order, or paste the bundle URL into any A _Hub canonical:_ https://memory.wiki/hub/raymindai _Concept digest:_ https://memory.wiki/raw/hub/raymindai?digest=1&compact=1