# Hjarni

> A hosted knowledge base with a built-in MCP server. Gives ChatGPT and Claude long-term memory. 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 tags
- Wiki-links between notes
- Custom AI instructions per folder, per team, or account-wide
- Built-in MCP server
- Full REST API
- File attachments (Pro plan)
- Team collaboration with shared folders
- Inbox for quick capture
- Export as Markdown ZIP, anytime

## Integrations

- ChatGPT: MCP custom connector
- Claude: Claude.ai, Claude iOS, Claude Desktop, Claude Code
- Any MCP-compatible AI assistant
- REST API for scripts and automations

## Positioning

- Notion is a workspace. Hjarni is a knowledge base built for AI.
- Obsidian is local-first with plugins. Hjarni is hosted with built-in MCP.
- ChatGPT Projects keep work inside ChatGPT. Hjarni keeps knowledge outside any one assistant.
- Claude Projects scope context to a project. Hjarni gives Claude persistent memory across conversations.
- Apple Notes is for capture. Hjarni is for AI memory.
- Mem bundles its own AI. Hjarni lets you bring ChatGPT or Claude.
- Reflect is a notes app with AI features. Hjarni is a knowledge base built for external AI.
- Khoj is open-source and self-hosted. Hjarni is hosted with zero setup.

## Pricing

Free plan available. Paid plans start at EUR 9/month. See [Pricing](https://hjarni.com/#pricing) for current details.

## Documentation

- [Getting started](https://hjarni.com/docs/getting-started): first steps and common setup mistakes
- [Use Hjarni with ChatGPT](https://hjarni.com/docs/chatgpt): connector setup
- [Use Hjarni with Claude](https://hjarni.com/docs/claude): Claude.ai, iOS, and MCP clients
- [What is MCP?](https://hjarni.com/docs/what-is-mcp): the protocol explained
- [MCP server reference](https://hjarni.com/docs/mcp): transport, OAuth, tools, and troubleshooting
- [REST API](https://hjarni.com/docs/api): endpoints, auth, pagination, examples
- [Notes in Markdown](https://hjarni.com/docs/notes): note model and formatting
- [Containers and tags](https://hjarni.com/docs/containers-and-tags): folder structure and labels
- [Wiki-links](https://hjarni.com/docs/wiki-links): bidirectional linking with stable IDs
- [Custom AI instructions](https://hjarni.com/docs/ai-instructions): per-folder and per-team rules
- [Teams and sharing](https://hjarni.com/docs/teams-and-sharing): team spaces and permissions
- [Export and data ownership](https://hjarni.com/docs/export-and-ownership): Markdown export, no lock-in
- [Privacy and permissions](https://hjarni.com/docs/privacy-and-permissions): what Hjarni does vs what your AI does
- [Templates](https://hjarni.com/docs/templates): pre-built workspace structures

## Use cases

- [For Developers](https://hjarni.com/use-cases/developers): architecture docs, conventions, debugging playbooks
- [For Researchers](https://hjarni.com/use-cases/researchers): literature notes, hypotheses, synthesis
- [For Founders](https://hjarni.com/use-cases/founders): strategy, meetings, decisions
- [For Writers](https://hjarni.com/use-cases/writers): style guides, research, drafts
- [For Travelers](https://hjarni.com/use-cases/travelers): preferences, past trips, itineraries

## Comparisons

- [Hjarni vs Notion](https://hjarni.com/compare/hjarni-vs-notion): workspace vs focused knowledge base
- [Hjarni vs Obsidian](https://hjarni.com/compare/hjarni-vs-obsidian): local-first vs hosted AI-native
- [Hjarni vs ChatGPT Projects](https://hjarni.com/compare/hjarni-vs-chatgpt-projects): project-scoped vs persistent memory
- [Hjarni vs Claude Projects](https://hjarni.com/compare/hjarni-vs-claude-projects): project-scoped vs reusable knowledge
- [Hjarni vs Apple Notes](https://hjarni.com/compare/hjarni-vs-apple-notes): personal capture vs AI-connected knowledge
- [Hjarni vs Mem](https://hjarni.com/compare/hjarni-vs-mem): bundled AI vs bring your own
- [Hjarni vs Reflect](https://hjarni.com/compare/hjarni-vs-reflect): AI inside vs AI alongside
- [Hjarni vs Khoj](https://hjarni.com/compare/hjarni-vs-khoj): self-hosted vs hosted simplicity

## Links

- [What is Hjarni?](https://hjarni.com/about)
- [FAQ](https://hjarni.com/faq)
- [Blog](https://hjarni.com/blog)
- [Sign up](https://hjarni.com/registration/new)