Hjarni for AI agents
Hjarni is a personal knowledge management platform for organizing, searching, and linking notes and tags. Individuals and small teams use it to keep this organized without extra manual upkeep. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Hjarni.
Create a note
Save a new note with content and tags from a conversation or research session.
Search notes by tag
Search notes tagged to a topic to gather background before writing a summary.
Restore a trashed note
Restore a note from the trash only after the user confirms it was deleted by mistake.
15 Hjarni actions, graded by risk.
Every Hjarni action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- hjarni.get_noteGet Note
- hjarni.list_tagsList Tags
- hjarni.list_notesList Notes
- hjarni.list_containersList Containers
- hjarni.get_account_statusGet Account Status
- hjarni.list_trashed_notesList Trashed Notes
write
8Create and change things. Allow, or ask the user first.
- hjarni.create_tagCreate Tag
- hjarni.create_noteCreate Note
- hjarni.update_noteUpdate Note
- hjarni.create_notesCreate Notes
- hjarni.create_containerCreate Container
- hjarni.update_containerUpdate Container
- hjarni.rename_tagRename Tag
- hjarni.restore_noteRestore Note
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- hjarni.trash_noteMove Note to Trash
Hjarni in three steps.
- 01Your users connect HjarniThey add their Hjarni api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “move Note to Trash” can be denied outright.
- 03Any agent can actYour agent calls Hjarni through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('hjarni', { read: 'allow', write: 'ask', // create_tag destructive: 'deny', // trash_note }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Hjarni connects.
Users add their Hjarni api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Hjarni connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Hjarni from any agent.
Hjarni and Arc0, answered.
Can I use Hjarni with Claude, ChatGPT or Cursor?
Yes. Connect Hjarni to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Hjarni actions you allow.
How do users connect Hjarni?
Users add their Hjarni api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Hjarni actions can my agent take?
15 in total: 6 read, 8 write and 1 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Hjarni?
Yes. Actions like “move Note to Trash” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Hjarni too?
Yes. The same Hjarni connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Hjarni into your agent.
Your users connect Hjarni once, under your brand. Your agent gets 15 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan