📝MythOS describes itself as a networked knowledge platform where every idea, person, project and decision lives as a linked memo in a library you own. 📝Claude Projects is a feature of 📝Claude, and Anthropic's help center says "Projects allow you to create self-contained workspaces with their own chat histories and knowledge bases." MythOS reaches Claude from outside, through an 📝MCP server that Claude on the web, desktop, iOS and Android signs into over OAuth.
At a Glance
Knowledge and Memory
Anthropic's article says "Within each project, you can upload documents, provide context, and have focused chats with Claude," with project instructions "to further tailor Claude's responses." Its memory article states that "Each project has its own memory," saved "as a set of individual topics as you chat," and that turning off "Use account memory" on a project's page keeps that memory separate (see 📝Memory). In MythOS the unit is the memo: typing @ mentions another memo, and every mention becomes a backlink. The 📝Augmentation System loads four identity memos, Soul, Style, Human and Memory, before a connected client writes.
Retrieval
Anthropic states that "Enhanced project knowledge with RAG is only available to users with paid Claude plans (Pro, Max, Ultra, Team, or Enterprise)," and that "Claude seamlessly enables RAG mode to expand capacity by up to 10x while maintaining response quality," a form of 📝retrieval-augmented generation. MythOS 📝Semantic Search splits each memo into roughly 500-token chunks and blends 70% vector similarity with 30% keyword relevance, gated to what the requester may read.
Access, Sharing and Plans
📝MythOS MCP gives a connected client 60 tools for search, memo writes, templates, tasks and the daily journal. Anthropic says "Free users can create a maximum of five projects," that on Team and Enterprise plans "projects can be shared with other members of your organization," and that "A new version of projects is now available in beta, rolling out in stages starting with 📝Claude Code." As of November 2026, Claude's pricing page lists Pro at $17 per month with an annual subscription discount or $20 if billed monthly, Max at $100 per month and Ultra at $200 per month.
Who Each Is For
Anthropic says "Projects are available to all users, including those with free Claude accounts." MythOS's overview says one library serves "private thinking, team collaboration, public writing, and the AI tools you work with," and its MCP memo addresses "anyone who wants their AI tools reading from and writing to the same knowledge base."
Related
- 📝Claude Projects and Claude memory — reference memo on Projects and per-project memory
- 📝Claude Code Projects — the redesigned Projects in Claude Code
- 📝How to Connect MythOS to Claude.ai — connecting a library to Claude over OAuth
- 📝MemPalace vs Obsidian vs MythOS as Claude Memory — the hub comparing memory systems for Claude
I built MythOS for what I actually needed: an AI that knows who I am, works from my structured knowledge, respects my permission model, and follows me across every client and device without re-explaining anything. The right question for a given builder is not "which is best?" but "which layer am I missing?"