Documentation
Docs
Hjarni is a Markdown-based knowledge base with a built-in MCP server. These docs cover setup, concepts, and integrations.
Reading paths
New user
AI user
Developer
Connect your AI 7 guides
Set up Hjarni by talking to your LLM
Paste one URL into ChatGPT or Claude and let your AI handle the MCP connection, the folder structure, and the first notes.
Use Hjarni with ChatGPT
Set up Hjarni as a connector in ChatGPT and verify the connection.
Use Hjarni with Claude
Connect via Claude.ai, Claude iOS, Claude Desktop, or Claude Code.
Auto-capture Claude Code sessions
Wire a Claude Code Stop hook to the Hjarni API so every session becomes a note.
Auto-capture Codex CLI sessions
Same pattern for Codex: a Stop hook writes every session to Hjarni as a growing note.
Use Hjarni with OpenClaw
Give your OpenClaw agent access to your notes via MCP.
Use Hjarni with Zapier
Automate note creation from 9,000+ apps through Zapier.
Hjarni for your AI tool 22 clients
Short landing pages with the exact MCP config for each client. See the compatibility matrix for every client at a glance.
Product concepts 7 guides
Notes in Markdown
The storage model: body, summary, source URL, tags, links, files, and version history.
Note history and Trash
Versioned edits with provenance (you vs your AI), view and revert to any earlier version, and a recoverable 30-day Trash.
File attachments
Attach PDFs, images, and other files to a note so your AI can read them too. Free includes 20 MB across five personal files.
Containers and tags
Use containers for structure and tags for cross-cutting labels.
Wiki-links between notes
Bidirectional links so your AI can follow relationships, not just folders.
Custom AI instructions
Set global, personal, container, or team rules for how assistants should work.
Templates
Bootstrap a workspace structure through your connected assistant.
Teams and trust 10 guides
Teams and sharing
Team spaces, collaborators, and who can access what.
Set up your team
Create a team, structure shared folders, set team-level AI instructions, and invite your teammates. A step-by-step first-day setup.
Team billing and seats
How team pricing works: free to start, then per seat. What a seat includes, when seats bill, and how to manage them.
Single sign-on (Enterprise)
SAML 2.0 for login, SCIM 2.0 for provisioning. Works with Okta, Microsoft Entra, Auth0, and any SAML IdP.
Share a folder publicly
Turn any folder into a read-only public page. Sub-folders, notes, and attachments come with it.
Team audit log (Enterprise)
Per-team log of every view, edit, and access change across web, API, MCP, and public links. Available on request.
Privacy, permissions, and AI boundaries
What Hjarni does, what ChatGPT or Claude does, and what a connection grants.
Export and data ownership
What you can export, what format it uses, and what stays portable.
Import from Obsidian or Markdown
Bring your vault in with folders, wiki-links, and attachments intact.
Open Knowledge Format (OKF)
Export your knowledge as an OKF bundle: Markdown, YAML front-matter, folders, links, and a change log any AI agent can read. How OKF maps to Hjarni.
MCP and integrations 14 pages
What is MCP?
Model Context Protocol explained: what it is, how it works, who supports it.
MCP vs API
APIs are for your code. MCP is for your AI. When to use each.
MCP vs Custom GPTs
Uploaded files go stale. MCP gives your AI a live connection to the source.
Connect any MCP server to ChatGPT
General guide for adding any MCP server to ChatGPT.
Connect any MCP server to Claude
General guide for adding any MCP server to Claude.ai, Desktop, or Code.
Connect GitHub Copilot to MCP
Add an MCP server to Copilot Chat in VS Code via mcp.json. Mind the servers key.
Connect Copilot Studio to MCP
Add a server to a Microsoft Copilot Studio agent through the MCP onboarding wizard, plus the streaming-timeout fixes.
Connect Perplexity to MCP
Add a custom MCP connector so Perplexity can read your own notes.
Connect Cursor to MCP
Add any MCP server to Cursor via mcp.json, global or per-project, with OAuth on first run.
Connect Raycast to MCP
Install an MCP server in Raycast AI and ask your own notes from anywhere on the desktop.
MCP reference
Transport, OAuth, tools, prompts, limits, and troubleshooting.
REST API reference
Authentication, pagination, endpoints, request shapes, and response examples.
MCP Config Validator
Paste a claude_desktop_config.json and catch JSON errors, missing fields, and typos in your browser.
MCP fixes
The configuration errors that show up the first time you wire an MCP server into Cursor, Claude Desktop, Claude Code, ChatGPT, or VS Code. Each page is a focused, copy-paste fix.
Conceptual background 5 guides
AI Glossary
Plain-language definitions for MCP, RAG, AI agents, second brains, and the terms that show up around them.
What is a second brain?
The concept, how AI changes it, and what to look for in a second brain app.
What is RAG?
Retrieval-Augmented Generation: how AI models look up your data before they answer, and where MCP fits.
What is an AI agent?
Models that pick tools, call them, and run in a loop. How agents differ from chatbots, and how memory keeps them useful between runs.
How to give your AI long-term memory
Stop re-explaining yourself. Connect your AI to an external knowledge base.
Can't find what you need?
Email evert@hjarni.com and we'll help.
Start here
Write once. You both remember.
Free to start. No credit card required.
Works with Claude and ChatGPT today.