Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Hjarni REST API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhjarni.com%2Fhjarni" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fhjarni.com%2Fhjarni" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Hjarni REST API.
Search notes by keyword across the knowledge base
Write new Markdown notes and revise existing ones
Organize notes into nested folders and reorder them
Link related notes together and list a note's linked notes
Tag notes and merge duplicate tags into one
GET STARTED
Archive, trash, and restore notes and folders
Read a note's revision history and revert it to an earlier version
Patterns agents use Hjarni REST API for, with concrete tasks.
★ Shared Human-and-Agent Notes
Keep one Markdown knowledge base that both people and an agent read and update, rather than a separate store the agent cannot see. The API searches notes by keyword, returns a note's full content by id, and updates it in place, so an agent can append findings to the same note a person is editing. Research and documentation teams use this to keep a single source of notes current.
Call GET /search to find a note, GET /notes/{id} to read it, then PATCH /notes/{id} to append the new content.
Knowledge Base Organization
Sort notes into nested folders and keep tags consistent so a growing knowledge base stays navigable. The API creates folders, called containers, and moves notes between them, and it can merge duplicate tags into a single canonical tag. Teams use this to reorganize a note collection without manual drag-and-drop in the app.
POST /containers to create a folder, then PATCH /notes/{id}/move to move each matching note into it.
Linked Notes and Backlinks
Connect related notes so a knowledge graph forms across the base and backlinks stay discoverable. The API links two notes, lists the notes linked to a given note, and can remove a link when it no longer applies. Writers use this to weave reference notes into a navigable web.
POST /notes/{id}/link to connect two notes, then GET /notes/{id}/linked to confirm the link was created.
Agent-Maintained Knowledge Base
An AI agent keeps a Markdown knowledge base current by searching existing notes, reading the relevant ones, and writing a consolidated summary note. Through Jentic the agent discovers the search and note operations, loads their schemas, and chains them without bespoke client code. This lets a research assistant capture and file knowledge directly.
Search Jentic for 'search notes', call GET /search, read candidates with GET /notes/{id}, and file a summary with POST /notes.
46 endpoints — the hjarni rest api reads and writes the same markdown notes, folders, and tags that its knowledge base shares between people and ai assistants.
METHOD
PATH
DESCRIPTION
/search
Search notes by keyword
/notes
List notes
/notes
Create a note
/notes/{id}
Get a note
/notes/{id}
Update a note
/notes/{id}/link
Link two notes
/containers
List folders
/tags
List tags
/search
Search notes by keyword
/notes
List notes
/notes
Create a note
/notes/{id}
Get a note
/notes/{id}
Update a note
/notes/{id}/link
Link two notes
/containers
List folders
/tags
List tags
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Hjarni by hand means handling its bearer auth and reading pagination totals out of the X-Total-Count, X-Page, and X-Per-Page headers yourself. Through Jentic you install once, import Hjarni from the API Directory, store the token once, and your agent calls the note and folder endpoints.
Permission scoping
Hjarni puts the note and folder id in the URL path, such as /notes/{id} and /containers/{id}, so a rule can pin your agent to read operations like searching and fetching notes. You choose the operations it may call, so destructive ones like moving a note to the Trash are not included unless you add them.
Credential isolation
Your Hjarni bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search notes' or 'create a note in a folder', and Jentic returns the matching Hjarni operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Hjarni REST API through Jentic.
Is there a Hjarni MCP server?
You do not need an MCP server to give your agent the Hjarni knowledge base. Jentic connects it directly from the API Directory: import Hjarni, store your bearer token once, and your agent calls the note, folder, and tag endpoints. Operations are discovered on demand, so no extra server's tool definitions load into the agent's context.
What authentication does the Hjarni REST API use?
The Hjarni REST API authenticates with a bearer token in the Authorization header, per its OpenAPI spec, and GET /me returns the account and token for a given key. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I search and update notes with the Hjarni REST API?
Yes. GET /search finds notes by keyword, GET /notes/{id} returns one note's full Markdown, and PATCH /notes/{id} updates it in place. List responses page with page and per_page and report totals in the X-Total-Count, X-Page, and X-Per-Page headers.
What are the rate limits for the Hjarni REST API?
The Hjarni spec documents a limit of 100 requests per minute per account across all of its tokens, and going over returns 429 with a Retry-After header. Back off for the number of seconds the Retry-After header indicates.
How do I search notes through Jentic?
Search Jentic with the query 'search notes', load the schema for GET /search, and execute it with your keyword, then read matches with GET /notes/{id}. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Hjarni REST API?
Yes. Write a rule that allows only GET /search, GET /notes, and GET /notes/{id}, so the agent can find and read notes but cannot create, move, or trash them, and every call it makes is logged. Because note ids live in the URL path, you can even confine a read to a single note.
For Agents
Search, write, and organize Markdown notes in a shared knowledge base: create notes, move them between folders, tag and link them, and read revision history.
Use for: Search my notes for a keyword, Create a new note inside a folder, Move this note into another folder, Link these two related notes together
Not supported: Does not send email, manage calendars, or run real-time chat. Use for reading and writing Markdown notes, folders, and tags only.
The Hjarni REST API reads and writes the same Markdown notes, folders, and tags that its knowledge base shares between people and AI assistants. It searches notes by keyword, writes and revises them, organizes them into nested folders called containers, links related notes, and tracks each note's revision history. Use it to let an agent maintain a durable Markdown knowledge base alongside the people editing it.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>