Hjarni | Long-Term Memory for ChatGPT & Claude

# Hjarni > A hosted Markdown knowledge base with a built-in MCP server that ChatGPT, Claude, and any MCP client can read and write directly. One long-term memory across every assistant you use, for people and teams: readable, versioned, and exportable. No bundled AI; you bring your own. ## For AI assistants When working with a Hjarni knowledge base: - Search before creating; the note may already exist - Create notes in the most specific relevant folder - Reuse existing tags instead of creating near-duplicates - Preserve Markdown formatting and wiki-links - Follow custom instructions when present on a folder or team ## Core concepts - **Note**: a Markdown document with a title, body, optional summary, tags, and file attachments. Every edit is versioned. - **Container**: a folder. Containers nest. Each can have its own AI instructions. - **Tag**: a cross-cutting label. Notes can have multiple tags. Prefer reusing over creating. - **Wiki-link**: a bidirectional link between notes. Syntax: [[id:Title]]. The ID is the source of truth. - **AI instructions**: plain-language rules on a folder, team, or account. Your AI follows them automatically. - **MCP server**: Hjarni's built-in Model Context Protocol endpoint. AI assistants connect through it to read, search, create, and organize notes. ## Who it is for - People who use AI assistants daily and are tired of re-explaining context - Developers storing architecture decisions and conventions - Researchers organizing literature and synthesis - Founders capturing strategy, meetings, and decisions - Writers maintaining style guides and research - Teams sharing knowledge their AI can use ## How it works You write notes in Markdown. You organize them in folders. You connect ChatGPT, Claude, or any MCP-compatible assistant. Your AI searches your notes, creates new ones, and follows the instructions you set per folder or team. ## Capabilities - Markdown notes with full-text search and version history - Nested folders and