--- title: "What is Memory.Wiki" url: https://memory.wiki/what-is-mdfy updated: 2026-05-24T15:23:17.278Z hub: https://memory.wiki/hub/raymindai bundle_count: 1 concept_count: 12 source: "mdfy-content" --- # What is Memory.Wiki *Personal knowledge hub for the AI era.* Memory.Wiki is a single URL that holds everything you've ever asked an AI worth keeping, and that any AI tomorrow can read as your context. ## The one-line version A captured ChatGPT answer becomes `memory.wiki/`. Forty captures roll up into `memory.wiki/hub/`. You paste that hub URL into Claude, ChatGPT, Cursor, or Codex and they fetch the whole thing as your personal knowledge layer. Same URL, every AI. ## Why a URL Vendor memory layers (ChatGPT memory, Claude projects, Cursor docs) all live behind walls. They don't talk to each other, you can't share them, and you can't paste them into the *other* tool tomorrow. A public URL is the one format every AI already knows how to read. No SDK, no plugin, no MCP server required. The URL is the contract; Memory.Wiki makes the URL. ## Three primitives, one shape - **Document** at `memory.wiki/` is one captured answer, paper, or transcript. - **Bundle** at `memory.wiki/b/` is a curated grouping of docs around a topic, with its own URL. - **Hub** at `memory.wiki/hub/` is your whole knowledge layer as a single deployable URL. Same URL primitive, three scopes. Each one is plain markdown when an AI fetches it. ## Three operations - **Capture**: paste a share URL, drop a file, or run `/memory.wiki capture` from any coding agent. - **Organize**: captures roll up into your hub; bundles group by topic; auto-synthesis merges new captures into existing wiki pages. - **Deploy**: paste any of the three URLs into any AI and it loads the underlying markdown as context. Or hit `/api/hub//recall` for question-targeted retrieval. ## What's not on the surface Underneath, every doc, chunk, and bundle is automatically embedded (OpenAI `text-embedding-3-small`, idempotent on save). Hybrid BM25 + vector RRF retrieval. Hub-wide semantic graph. Cross-hub citation rollup. The pipeline rivals what backend-only memory systems give you, but the surface stays human-shaped. The cross-AI claim is independently verifiable. [MWBench](/mwbench) is the open eval that measures whether one URL actually works across Claude, OpenAI, and Gemini: 100% accuracy, including on content the AIs have never seen during training, with every answer audited against a literal corpus quote. For the architecture, see [How Memory.Wiki works](/how-memorywiki-works) and [How Memory.Wiki Memory works](/mw-memory). --- ## Summary Memory.Wiki is a vendor-neutral URL-based personal knowledge system that lets users capture and organize AI conversations and documents in a single hub that any AI can read as context. The core innovation is replacing vendor-locked memory layers with a shareable markdown URL that works across ChatGPT, Claude, Cursor, and other AI tools without requiring SDKs or plugins. ## Themes - Cross-AI portability - URL as infrastructure - Knowledge layer standardization ## Key takeaways - Memory.Wiki stores captured AI answers and documents at URLs that remain the same across different AI platforms (Claude, ChatGPT, Cursor, Codex). - Three URL primitives exist: Document (single answer), Bundle (curated topic grouping), and Hub (complete personal knowledge layer). - All content in the system is automatically embedded and retrievable through both direct URL fetch (returns plain markdown) and API-based semantic retrieval. - The system is independently verified through MWBench evaluation to work across Claude, OpenAI, and Gemini with 100 percent accuracy. - Vendor memory systems are locked behind walls and cannot share content between platforms, while Memory.Wiki uses public URLs as the universal interface. ## Insights - Memory.Wiki solves vendor lock-in by making the URL itself the universal contract that all AI systems already understand, eliminating need for SDKs or plugins. - The system treats documents, bundles, and hubs as the same primitive at different scopes, creating a fractal knowledge structure that scales from single captures to entire personal knowledge bases. - Sophisticated retrieval (hybrid BM25 plus vector search with semantic graphs) is hidden behind a simple surface, allowing humans to interact through basic markdown while sophisticated indexing happens transparently. ## Open questions / gaps - What happens to embedded vectors and retrieval indices if a user deletes or significantly modifies a document? - How does the auto-synthesis feature decide which new captures should merge into existing wiki pages versus remain separate documents? ## Concepts in this document - **memory.wiki** _(entity)_ The primary product platform being developed and documented. - **Chrome extension** _(entity)_ Surface within memory.wiki ecosystem. - **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. - **MCP server** _(concept)_ A standard protocol allowing diverse AI tools to query and interact with the memory.wiki hub. - **Hybrid Retrieval** _(concept)_ Technical approach combining chunked indexing with semantic search for precise question-targeted recall. - **URL as API** _(concept)_ Core architectural principle where every Memory.Wiki URL serves as a fetchable API endpoint for AI consumption - **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. - **AI memory** _(tag)_ Conceptual topic describing how memory is used by AI agents. - **URL Architecture** _(concept)_ Shared URL structure between web and iOS to maintain canonical document and profile access. - **Cross-AI Compatibility** _(concept)_ The ability for Memory.Wiki URLs to work across any AI tool without vendor lock-in ## Concept relations (within this doc's concepts) - **AI memory** disrupts category **Knowledge Management** - **memory.wiki** targets platform **Claude** - **memory.wiki** targets platform **ChatGPT** - **memory.wiki** targets platform **Cursor** - **URL as API** integrates with **ChatGPT** - **memory.wiki** exposes through **MCP server** - **URL as API** integrates with **Claude** - **Chrome extension** captures to **memory.wiki** - **Cross-AI Compatibility** enables through **URL as API** - **memory.wiki** implements **URL as API** - **Hybrid Retrieval** serves domain **Knowledge Management** - **URL as API** implements pattern **Cross-AI Compatibility** - **URL as API** enables compatibility **Cross-AI Compatibility** - **Cursor** saves decisions to **memory.wiki** - **Claude** loads context from **memory.wiki** - **URL as API** enables **Cross-AI Compatibility** - **Chrome extension** feeds data to **memory.wiki** - **memory.wiki** utilizes as protocol **MCP server** - **memory.wiki** provides surface for **Chrome extension** - **Claude** has isolated **AI memory** ## 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