# mdfy Demo's knowledge hub

> A hand-curated example hub showing what mdfy makes possible — captured AI conversations, research notes, project decisions, and the bundles that synthesise them. Paste any URL into Claude, ChatGPT, or Cursor to see the full payload.

Canonical hub URL: https://memory.wiki/hub/demo
Agent operating manual: https://memory.wiki/hub/demo/AGENTS.md
Wiki manifest (concept-grouped TOC): https://memory.wiki/hub/demo/index.md
Wiki schema (what URLs are available + how to use them): https://memory.wiki/hub/demo/SCHEMA.md
Activity log (public events only): https://memory.wiki/hub/demo/log.md
Lint report (orphan + duplicate findings): https://memory.wiki/raw/hub/demo/lint.md
Index (full markdown listing): https://memory.wiki/raw/hub/demo?compact=1
Concept digest (densest summary): https://memory.wiki/raw/hub/demo?digest=1&compact=1
Full text (every doc concatenated, capped to fit a context window): https://memory.wiki/hub/demo/llms-full.txt

Hub size: ~27,549 tokens across 55 public documents.
Every document below is also available as `https://memory.wiki/raw/<id>?compact=1` for token-economical fetches.

## Documents
- [API conventions](https://memory.wiki/LhYW7tc1) — ~393 tokens
- [Open questions](https://memory.wiki/ir0K6-u2) — ~447 tokens
- [Decision log](https://memory.wiki/SrgEHFCI) — ~619 tokens
- [UI patterns](https://memory.wiki/wp12y7sM) — ~419 tokens
- [DB schema notes](https://memory.wiki/HsxL91R7) — ~377 tokens
- [Auth pattern — Supabase Auth + RLS](https://memory.wiki/mjpt9oz8) — ~359 tokens
- [Acme Pulse — project README](https://memory.wiki/SWys7jXa) — ~410 tokens
- [PDF import test](https://memory.wiki/ta8mE-Dk) — ~68 tokens
- [Claude prompts I keep reusing](https://memory.wiki/wzixoDcN) — ~623 tokens
- [Welcome to [mdfy.app](http://mdfy.app)](https://memory.wiki/2WqRPNiV) — ~658 tokens
- [Onboarding script: 5 slides](https://memory.wiki/Ts4Vh6Zw) — ~551 tokens
- [How Claude should read this hub](https://memory.wiki/NFnDceE2) — ~622 tokens
- [RFC: 3-state permission model](https://memory.wiki/El2-Kzy6) — ~643 tokens
- [Mermaid: 6 diagram types side by side](https://memory.wiki/9uh4qUuz) — ~541 tokens
- [Tables: alignment, code, math inline](https://memory.wiki/hjlgK4OA) — ~440 tokens
- [Microsoft GraphRAG: what we learned](https://memory.wiki/6WkjlKgA) — ~581 tokens
- [Mem0 vs Letta: extracted memory comparison](https://memory.wiki/_ybJOqIB) — ~553 tokens
- [What I'm NOT doing](https://memory.wiki/q13ymHpq) — ~609 tokens
- [Decision: Anthropic Haiku for hub-recall reranker](https://memory.wiki/sB3a5eOG) — ~383 tokens
- [Karpathy wiki: the parts that map](https://memory.wiki/glqi_Xjw) — ~566 tokens
- [Cross-AI as a structural moat](https://memory.wiki/1tyw7rGT) — ~629 tokens
- [Pricing experiments planned (restricted)](https://memory.wiki/VZI8WpeB) — ~584 tokens
- [YC mock interview notes](https://memory.wiki/1fCfQkpa) — ~574 tokens
- [Decision: Keep the Markdown engine in Rust + WASM](https://memory.wiki/5DWOm2ya) — ~416 tokens
- [Gemini on diagram prompting](https://memory.wiki/qP599HA4) — ~408 tokens
- [Claude on Rust performance pitfalls](https://memory.wiki/77bvsdJ4) — ~523 tokens
- [Claude pair: writing the v6 onboarding overlay](https://memory.wiki/igQZHNzq) — ~501 tokens
- [Decision: Supabase pgvector over Pinecone](https://memory.wiki/frK9IDOy) — ~463 tokens
- [Decision: Inline graph_data in bundle URLs](https://memory.wiki/yIpXMsqc) — ~455 tokens
- [Decision: Drop [[wikilinks]] permanently](https://memory.wiki/DDxqHKdd) — ~513 tokens
- [Context engineering: where it goes next](https://memory.wiki/AXAIfrBG) — ~536 tokens
- [llms.txt adoption: who's actually shipping it](https://memory.wiki/qKRfGtCa) — ~535 tokens
- [GTM: the three channels I'll work](https://memory.wiki/8MD8xlLA) — ~541 tokens
- [Launch day: what success looks like](https://memory.wiki/mXy_aztt) — ~479 tokens
- [Pricing model thoughts](https://memory.wiki/TQhyhtbt) — ~524 tokens
- [Math: every flavour we render](https://memory.wiki/y3zQ915R) — ~381 tokens
- [Investor outreach list (restricted)](https://memory.wiki/0-yqUYQx) — ~497 tokens
- [Founder journal (restricted)](https://memory.wiki/khPQfDFc) — ~598 tokens
- [README — start here](https://memory.wiki/csFtDM3c) — ~492 tokens
- [My current personal stack](https://memory.wiki/UaxcbLwD) — ~489 tokens
- [Mistakes I made building v6](https://memory.wiki/bDVLxgav) — ~774 tokens
- [Show HN plan (working draft)](https://memory.wiki/r_HaRypO) — ~629 tokens
- [Feature ideas backlog](https://memory.wiki/wyULEr1h) — ~542 tokens
- [Glossary](https://memory.wiki/_bhW7pVA) — ~666 tokens
- [RFC: hub recall API](https://memory.wiki/OGySiVoO) — ~659 tokens
- [GPT-5 on context-budget rituals](https://memory.wiki/EyW4HU4-) — ~404 tokens
- [mdfy MCP server: setup in 4 lines](https://memory.wiki/PrxR1Uj4) — ~534 tokens
- [Wiring mdfy into Claude Code](https://memory.wiki/iok3gZo6) — ~608 tokens
- [Wiring mdfy into Codex via AGENTS.md](https://memory.wiki/y4sEEo1R) — ~555 tokens
- [Karpathy's LLM Wiki concept, in one read](https://memory.wiki/T7ZGdpOm) — ~354 tokens
- [The structural moat: cross-AI portability](https://memory.wiki/rBRZ_nni) — ~368 tokens
- [Wiring mdfy into Cursor](https://memory.wiki/TEuiwop8) — ~326 tokens
- [Formatting tour: math, diagrams, code, tables](https://memory.wiki/F1q9U1YP) — ~376 tokens
- [Decision: ship graph_data inside the bundle URL](https://memory.wiki/kxn9T-Vv) — ~368 tokens
- [AI memory architectures: a Claude conversation](https://memory.wiki/yt2ZZqyI) — ~386 tokens

## Bundles
- [AI Memory Research](https://memory.wiki/b/wa-K_2rF): Captured conversations + external reading on how AI memory architectures actually work. Reading order: the Claude conver
- [Cross-tool dev workflow](https://memory.wiki/b/p_mdtSk0): Acme Pulse, a fictional landing-page builder. The seven docs in this bundle are the project's living context — README, a
- [Launch strategy: Show HN week](https://memory.wiki/b/DlrrKcQ2): Pre-launch plan + GTM channels + what not to do. The strategy bundle a reviewer can read end-to-end.
- [AI memory research: the public frontier](https://memory.wiki/b/wpwVCSDF): Side-by-side notes on Mem0, Letta, Microsoft GraphRAG, Karpathy's LLM Wiki, llms.txt adoption.
- [Engineering decisions + cross-AI strategy](https://memory.wiki/b/8IkpnVgX): A working bundle: the ADR for shipping graph_data in URLs, the cross-AI moat argument, and a hands-on integration note f
- [AI tool integration tour](https://memory.wiki/b/EJbI7cto): Claude Code, Codex (AGENTS.md), MCP server, Cursor — every wiring path the demo hub supports.

## Optional
- [Owner page](https://memory.wiki/hub/demo): rendered HTML view