MythOS
MythOS since 2017(not related to Anthropic Claude MythOS)

Stop re-explaining yourself to your AI.

MythOS is the shared memory between you and every AI you use. Capture what you read. Connect what you think. Publish what matters — across every model, every agent, every channel.

Create Your MythOS→Send me to explore
✓Yours forever✓Works with every AI✓Free to start

Your library, one click from every AI.

mythos.one/me/brianswichkow
Brian Swichkow's MythOS library — feed of memos with sidebar, stats, and chat panel
For people who write to think.

You already have a memory. It's just scattered across Notion pages, voice memos, half-written drafts, and every AI chat you've ever had.

WritersResearchersFoundersAnyone who thinks in public
Memory·Capture

Write once. Remember forever.

Markdown editor with @mentions, #hashtags, collapsible headings, and images that paste in like email. Your memos link to each other automatically. Your library builds itself.

See how memos work →
MythOS memo with hashtag chips and mention links
Memory·Cultivate

Build your library with your AI, not around it.

MythOS is designed to be co-authored. Ask Claude to research a topic — it writes the memo and files it for you. Use Cursor, Windsurf, or any MCP-native app, and your library follows. Every conversation ends with something permanent.

Connect via MCP →
CClaude
MCP · MythOS connected
Research portable AI memory. Make me a memo and file it under ai and memory.
Researching portable AI memory across 📝 MCP spec 📝 llms.txt and 📝 your prior notes. Drafting now…
✓ Saved to MythOS
📝 Portable AI Memory
7 sections · 1,240 words · 3 mentions
aimemoryresearch
Mind·Orchestrate

One library. Every workflow.

Drop a memo into any automation. Zapier reads from MythOS. Your n8n flow pulls your notes before firing. Your agent loads your library as context before replying. Your memory becomes the single source of truth the rest of your stack can actually reference.

See integrations →
📝
Source
MythOS Library
memos + tags + mentions, scoped by API key
→
⚙️
Process
Load + generate
inject as context, run agent, extract output
→
📤
Output
Wherever
Slack message
Email draft
API response
Runs in:Zapiern8nMakeCursorYour scripts
Mind·Ask

Talk to what you've written.

Every memo becomes searchable by meaning, not just keywords. Ask your library questions. Get answers grounded in your own words, with citations to the exact memo where you wrote them.

Try the chat →
Ask
Brian's library
What did I conclude about memory vs. context?
You've been consistent across four memos: memory is the shape of your thinking; context is the snapshot. In @portable-context you wrote that context dies on model migration, but memory persists as long as the vocabulary does.
Summarize my last week.
Brian's library is typing
Ask a question…▶
Mouth·Publish

Your library, out loud.

Publish any memo with one toggle. Readers get your prose, your mentions, your tags, and a chat panel that speaks in your voice — grounded in your own memos. Every memo is a live page. Every library is a live conversation.

See a public memo →

MythOS MCP

👤 Creator Brian Swichkow📅 Created · 3/30/2026🕐 Updated · 4/13/2026
Body

Objective

MythOS MCP — Model Context Protocol — connects your MythOS knowledge library to AI assistants like Claude, Cursor, and Windsurf.

It lets you search memos, read content, and sync changes — all from within your AI tools. This is the Memory layer of The Augmentation Stack.

Mouth·Broadcast

One source. Three channels.

Turn any public memo into a discussion space — upvote, comment, fork. Send it as a newsletter issue to your subscribers. Get surfaced in search — Google and every AI indexer, thanks to JSON-LD and /llms.txt. Your audience doesn't come to the platform; the platform goes to them.

See distribution →
we / second-brain·posted by @brianswichkow·4h
MythOS MCP — how I connect every AI to my library

A rundown of connecting Claude, Cursor, and Windsurf via MCP. Every conversation ends with a memo filed in my library. Feedback welcome.

▲247▼💬 38 comments⑂ 12 forks↗ share
Newsletter · Issue #42
Brian's Library — to 4,218 subscribers
Your memory shouldn't die when the AI does.

This week: connecting every AI you use to a single portable memory layer. One memo, many models. Plus: three experiments in agent-readable notes…

Free tier · 2,847 recipients58% open rate
mythos.one › me › brianswichkow › mythos-mcp
MythOS MCP — Connect every AI to your library

Model Context Protocol connects your MythOS knowledge library to AI assistants like Claude, Cursor, and Windsurf. Search memos, read content, sync changes…

Cited by ChatGPT · Perplexity · Claude.ai
Portable

Addressable by every AI you'll ever use.

MythOS publishes an llms.txt, serves an agent-scoped API, and speaks OpenAPI. Your Claude reads your library. Your ChatGPT reads your library. Your next model, trained next year, reads your library. Your memory doesn't die when the AI does.

zsh — mythos.one
# Any agent, any model, any script — same API.$ curl -H "x-mythos-key: mtk_•••••••" \ mythos.one/api/internal/memos?tag=memory { "memos": [ { "id": "…", "title": "How I think about memory", "updatedAt": "2026-04-10" }, { "id": "…", "title": "Portable context", "updatedAt": "2026-04-04" } ]} # Or just point any LLM at /llms.txt and let it discover everything.
ClaudeChatGPTGeminiGrokPerplexityYour agentsWhatever's next
Pricing

Simple tiers. Yours forever.

Free to start. Upgrade when your library outgrows you. Export everything anytime.

Free
$0
Get Started
  • 50 memos
  • Daily journal
  • Basic search
  • 1 AI chat thread
Scribe
$10 /mo
Get Started
  • Unlimited memos
  • Knowledge graph
  • Habit tracking
  • AI chat (BYOK)
  • Full-text search
Scholar
$50 /mo
Get Started
  • Everything in Scribe
  • MCP server access
  • Hash ingestion
  • Newsletter publishing
  • Unlimited collaborators
  • API access (60 req/min)
Oracle
$100 /mo
Get in Touch
  • Everything in Scholar
  • Custom landing page builder
  • Priority support
  • Full API access
  • Custom community
Questions

Before you ask.

Is this related to Anthropic's Claude "MythOS"?—

No. We've been MythOS since 2017 — years before Anthropic existed. If anything, it's the other way around.

What if I want to leave?—

Export everything as markdown anytime, including media. Your library is yours; we're just hosting it.

Do I need to know markdown?—

No. The editor works like any rich-text tool — bold, lists, checkboxes, images. Markdown is what we save underneath so it stays portable forever.

What AIs does this work with?—

Claude, ChatGPT, Gemini, Grok, Perplexity — anything that can speak HTTP or MCP. We publish an llms.txt and an agent-scoped API. Your next model will work too.

Can I bring my own AI key?—

Yes. Free and Pro both support BYO keys for OpenAI or Anthropic. Pro also includes hosted AI if you'd rather not manage keys.

Is my library private by default?—

Yes. Every memo starts private. You choose what to make public, unlisted, or shared with specific contacts via permission tags.

Your library. Your memory. Your everything-AI .

AboutPrivacyTermsContact

© 2026 MythOS · Since 2017 · Not related to Anthropic Claude MythOS