Install Jentic One Beta

Connect the HackMD API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the HackMD 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%2Fhackmd.io%2Fhackmd" | sh

Step 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%2Fhackmd.io%2Fhackmd" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with HackMD API.

Get the authenticated user's HackMD profile, name, and email

List, create, update, and delete personal notes in Markdown

Retrieve a note by id with its full Markdown content and permissions

Read recent edit history across the user's notes

List the teams the user belongs to with role and team path

GET STARTED

Start building with HackMD API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use HackMD API for, with concrete tasks.

★ Meeting Summary to Shared Note

Convert a transcribed meeting recording into a Markdown summary and post it as a HackMD note that the team can edit collaboratively. The agent calls POST /teams/{teamPath}/notes with the rendered Markdown and read/write permissions, then shares the returned URL with the channel. HackMD handles real-time co-editing once humans take over.

POST /teams/engineering/notes with title 'Sprint Planning 2026-06-10' and a Markdown body summarising the transcript, returning the note URL.

Documentation Pull-Then-Update

Maintain a runbook by pulling its current Markdown via GET /notes/{noteId}, asking an LLM to refresh it based on a recent incident, and writing it back via PATCH /notes/{noteId}. Useful for SRE teams keeping playbooks current without making humans hand-edit every time.

GET /notes/{noteId}, generate a refreshed Markdown body using the incident report, then PATCH /notes/{noteId} with the new content.

Personal Note Capture from Chat

Listen to a chat channel for messages tagged for personal capture and create matching HackMD notes via POST /notes. The agent organises notes by topic in the title and dumps the full message context into the body. Knowledge workers use this to consolidate scattered chat into searchable Markdown.

POST /notes with a title from the message subject and a body containing the full thread Markdown, then return the new note id.

Team Workspace Audit

List all teams the user belongs to and enumerate their notes for a content audit. The agent walks /teams to find team paths, then walks /teams/{teamPath}/notes to inspect titles, last-modified timestamps, and tag fields. Useful for cleaning up stale documentation in large organisations.

GET /teams, then for each team GET /teams/{teamPath}/notes and report any note unmodified for over 180 days.

Agent Discovery Through Jentic

Agents discover HackMD operations by searching Jentic with intents like 'create a markdown note'. Jentic returns the matching POST /notes operation with its input schema. The bearer token is stored in the vault, never in the agent prompt.

Use Jentic search 'create a markdown note' to find POST /notes and execute it with title and content fields.

Key Endpoints

12 endpoints — hackmd is a real-time collaborative markdown editor used by engineering teams, researchers, and educators for shared notes, meeting minutes, and documentation.

METHOD

PATH

DESCRIPTION

GET

/me

Get the authenticated user's profile

GET

/notes

List the user's personal notes

POST

/notes

Create a new personal note

PATCH

/notes/{noteId}

Update a personal note's content

GET

/history

Read recent edit history

GET

/teams

List the user's teams

POST

/teams/{teamPath}/notes

Create a note inside a team workspace

GET

/me

Get the authenticated user's profile

GET

/notes

List the user's personal notes

POST

/notes

Create a new personal note

PATCH

/notes/{noteId}

Update a personal note's content

GET

/history

Read recent edit history

GET

/teams

List the user's teams

POST

/teams/{teamPath}/notes

Create a note inside a team workspace

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the HackMD API by hand means setting its bearer token on every call and building each note, history, and team request yourself. Through Jentic you install once, import the HackMD API from the API Directory, store the token once, and your agent calls it.

Permission scoping

HackMD puts the team path in the URL (/teams/{teamPath}/notes), so a rule can pin your agent to one team workspace: it can create and list notes there and nothing else. You choose the operations it may call, so editing existing notes is not included unless you add it.

Credential isolation

Your HackMD 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 'create a markdown note' or 'list team notes', and Jentic returns the matching HackMD operation with its input schema so the agent calls the right endpoint without browsing the docs.

FAQs

Specific to using HackMD API through Jentic.

What authentication does the HackMD API use?

HackMD uses Bearer token authentication. Generate a token from the HackMD account settings under API tokens and pass it as Authorization: Bearer <token>. Through Jentic, the token stays encrypted in the vault and is injected at execution time so the agent never sees the raw value.

Can I create a Markdown note in a team workspace?

Yes. POST /teams/{teamPath}/notes with the title, content, readPermission, and writePermission fields creates the note inside the team. The teamPath is the slug shown in the team URL. The response returns the note id and shareable URL.

How do I update an existing HackMD note?

PATCH /notes/{noteId} updates the note's content and metadata. Pass the full new Markdown body in the content field. For team-owned notes, use PATCH /teams/{teamPath}/notes/{noteId} instead. The endpoint requires write permission on the note.

What rate limits apply to the HackMD API?

HackMD enforces per-token rate limits and returns 429 when exceeded. Public documentation lists a soft ceiling of around 100 requests per hour for read operations and a stricter limit for writes. Agents should respect 429 responses and back off.

How do I post a meeting summary to HackMD through Jentic?

Run pip install jentic, then search 'create a markdown note in a team' to find POST /teams/{teamPath}/notes. Load the schema, fill in title, content, and team path, and execute. The full flow takes under five minutes once the team path is known.

Can I see who edited a note recently?

GET /history returns recently edited notes for the authenticated user with last-changed timestamps, but the API does not expose a per-note revision diff. For collaborative authoring history, follow the note URL into HackMD's web UI which shows the full revision pane.

Can I limit what my agent is allowed to do with the HackMD API?

Yes. Because you run Jentic One yourself, your own rules decide which HackMD operations and credentials your agent may use. Since HackMD puts the team path in the URL such as /teams/{teamPath}/notes, you can pin the agent to a single team workspace and allow only the operations you pick, for example creating and listing notes there. Editing existing notes with PATCH /notes/{noteId} stays off unless you explicitly add it, and your bearer token is injected at execution time rather than exposed to the agent.

HackMD API

AI ReadinessAI-Aware (A-)72/100

See full scorecard

Community OpenAPI document · agent-readyProductivityCollaborationbearer12 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Read a HackMD user's profile, create and update personal or team notes in Markdown, and pull recent note history.

Use for: Get the HackMD profile of the current user, Create a new HackMD note titled 'Sprint Planning 2026-06-10' with Markdown body, Update an existing HackMD note with new content, List all notes belonging to the team with path 'engineering'

Not supported: Does not handle slide presentations, file attachments, or real-time chat - use for HackMD Markdown notes, history, and team workspaces only.

HackMD is a real-time collaborative Markdown editor used by engineering teams, researchers, and educators for shared notes, meeting minutes, and documentation. The API exposes operations to read the authenticated user's profile, manage personal notes, list note history, and manage notes that belong to a team. Agents can create, update, and delete notes programmatically, making HackMD a natural collaborative output target for AI writing and meeting-summary workflows.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B-Signals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

50%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C+Signals: 4

75%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

63%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

78%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the HackMD API to your agent

Capabilities

Start building with HackMD API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

HackMD API

Jentic AI Readiness Score

HackMD API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness