Enables Claude to pull curated context from self-hosted Markdown files via a remote MCP connector, with an append-only journal for agent notes manually promoted by the owner.
Enables AI clients to read and write to a user-owned markdown bucket via S3-compatible storage, providing a persistent shared context layer across different AI tools.
Enables LLMs to access a user's personal writing context—voice, style, opinions, expertise, projects, and communication patterns—via curated markdown files, helping the LLM match the user's voice when generating written content.
MCP server for privacy-gated local Apple data access including Mail, Messages, Notes, Calendar, Contacts, Photos, Reminders, Voice Memos, and iCloud Drive.
Parses an Obsidian vault and exposes structured context (notes, blocks, tasks, headings) through MCP tools, enabling AI clients to query and reason over local markdown notes.
An open-source memory layer that provides persistent project context and architectural history for AI development tools across multiple platforms and sessions. It enables AI assistants to maintain a shared understanding of codebases while integrating directly with services like Notion for documentation management.
A native Nextcloud app that exposes the instance as an MCP server so Claude and other MCP clients can read, search, and (with admin-granted permissions) edit files, notes, calendars, Deck cards, and Talk conversations. It runs inside Nextcloud with OAuth or app-password sign-in, applying each user's own Nextcloud permissions and admin-controlled per-operation grants.
Lets AI agents retrieve source-linked passages from a local folder of Markdown notes or an Obsidian vault, optionally following the explicit links between notes, and can also fetch passages from pinned public GitHub files you configure. It returns bounded evidence packets with original text, file paths and hashes so agents can answer from your material rather than generating content themselves.
Enables a local-first Codex plugin to maintain durable OKF memory, manage scoped project and personal context, and perform reviewed selective encrypted exports and recovery.
Give your AI persistent, structured memory and let humans see it too. It stores project knowledge as Markdown files in a hierarchical tree, accessible via MCP tools and a built-in Web UI.
A live MCP server that connects AI assistants to a running Obsidian instance, enabling full app automation including reading notes, clicking UI elements, managing plugins, and executing JavaScript.