Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Luna 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%2Fgetmyluna.app%2Fgetmyluna" | 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%2Fgetmyluna.app%2Fgetmyluna" | 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 Luna API.
Log, edit, react to, and undo baby-care events such as feeds, sleep, and nappies
List today's events and the events for any chosen day
Return growth measurements and weekly pattern reviews for a child
Invite and revoke caregiver access to a shared family account
Create and revoke bearer tokens for connecting an assistant
GET STARTED
Answer questions over the family's own logged history
Patterns agents use Luna API for, with concrete tasks.
★ Agent-logged care events
An AI assistant a parent talks to can call the Luna API through Jentic to log a feed or nap as it happens and read back today's events to confirm. Jentic returns the log-event operation from a natural-language query, so the assistant records care without the parent opening the app or the assistant reading the Luna reference.
Log a feed event with the current time for the family, then list today's events and confirm the feed was recorded.
Weekly pattern review
Return growth measurements and the weekly pattern review to show how a child's sleep and feeding are trending across a shared family account. Parents and caregivers use this to spot changes in routine without scrolling the raw event log.
Read the child's growth measurements and the weekly pattern review, then summarize how sleep and feeding changed this week.
Caregiver access management
Invite a caregiver to the family account, list open invites and members, and revoke access when it is no longer needed, all scoped to one family resolved from the credential. Families use this to share the same care log with a nanny or grandparent without exposing another family's data.
Create a caregiver invite link for the family, list the current members and open invites, and confirm the new invite appears.
40 endpoints — the luna api is the shared baby-care tracker behind the luna app, recording feeds, sleep, nappies, solids, and routines for one family across parents and invited caregivers.
METHOD
PATH
DESCRIPTION
/api/vega/onboard
Create a family account
/api/vega/log
Log a care event
/api/vega/today
List today's events
/api/vega/events
List events for a day
/api/vega/measurements
Retrieve growth measurements
/api/vega/patterns
Retrieve patterns and weekly review
/api/vega/invite
Create a caregiver invite link
/api/vega/token
Create a bearer token
/api/vega/onboard
Create a family account
/api/vega/log
Log a care event
/api/vega/today
List today's events
/api/vega/events
List events for a day
/api/vega/measurements
Retrieve growth measurements
/api/vega/patterns
Retrieve patterns and weekly review
/api/vega/invite
Create a caregiver invite link
/api/vega/token
Create a bearer token
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Luna API by hand means creating a bearer token in the app or from a signed-in session, handling the one-family scoping, and coding each logging and review call yourself. Through Jentic you install once, import the API from the API Directory, store the token once, and your agent calls it.
Permission scoping
The Luna endpoints resolve the family from the credential rather than from an id in the URL path, so bound your agent to the operations it needs, such as logging events and reading the day. You choose which operations it may call, so the delete-family operation is not included unless you add it.
Credential isolation
Your Luna 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 'log a feed' or 'review this week's patterns', and Jentic returns the matching Luna operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Luna API through Jentic.
Is there a Luna API MCP server?
You do not need an MCP server to give your agent the Luna API. Jentic connects it directly from the API Directory: import the API, store your token once, and your agent calls the logging, review, and account operations. Operations are discovered on demand, so no extra server definitions load into the agent's context.
What authentication does the Luna API use?
Most endpoints require a bearer token per the OpenAPI spec, with a session cookie named luna_session accepted for the web app, while public endpoints such as the health check and connector manifest need no credential. Through Jentic the token is stored encrypted in your own Jentic One instance and supplied only when an authenticated call runs, so it never reaches the agent's context.
Is Luna API data scoped to one family?
Yes. Every request is scoped to a single family resolved from the bearer token or session cookie, and there is no way to address another family's data. That means a connected assistant only ever sees and writes to the family whose token it holds.
What are the rate limits for the Luna API?
The OpenAPI spec does not specify rate limits. A health endpoint lets you check service status, and you can confirm the current request limits in the Luna documentation at https://getmyluna.app.
Can I limit what my agent is allowed to do with the Luna API?
Yes. Write a rule that permits only the logging and read operations, such as logging a feed and listing today's events, so the agent can track care but cannot run the delete-family operation, and every call it makes is logged.
How do I log a care event with the Luna API through Jentic?
Search Jentic for 'log a baby feeding event' to surface the log-event operation, load its input schema, pass the event type and time, and execute, then list today's events to confirm. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Track baby care across a shared family account: log feeds, sleep, and nappies, review today's events and growth patterns, manage caregiver invites, and read the family's history.
Use for: Log a feed for the baby right now, List today's care events for my family, Review this week's sleep and feeding patterns, Invite a caregiver to the family account
Not supported: Does not provide medical advice, clinical records, or appointment booking. Use for shared baby-care activity tracking across a family only.
The Luna API is the shared baby-care tracker behind the Luna app, recording feeds, sleep, nappies, solids, and routines for one family across parents and invited caregivers. It logs, edits, reacts to, and undoes care events, lists today's and any day's events, and returns growth measurements and weekly pattern reviews. It manages the family account, caregiver invites, child profile, and bearer tokens, and every request is scoped to a single family resolved from the credential so no caller can reach another family's data. It also answers questions over the family's own history through its Ask Luna feature. It is aimed at parents and tools that want programmatic access to a shared care log.
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>