Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Aurora Platform 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%2Faurorainbox.com%2Faurorainbox" | 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%2Faurorainbox.com%2Faurorainbox" | 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 Aurora Platform API.
Send a message into an existing chat via POST /Chats/{id}/Messages
Open a new chat with a contact through POST /Chats and route it to a team
Search the chat history with POST /Chats/Search and filter by channel or contact
Upsert a contact via POST /Contacts/Upsert to keep CRM records in sync
List WhatsApp Business and WhatsApp Cloud channels available to the workspace
GET STARTED
Track sales pipeline through GET and POST /Opportunities tied to a contact
Subscribe to inbound message events via the Webhooks endpoints
Patterns agents use Aurora Platform API for, with concrete tasks.
★ WhatsApp customer support automation
Support teams receive thousands of inbound WhatsApp messages and need an AI tier to triage and reply to common questions. Webhooks from Aurora Inbox notify the agent of a new message; the agent calls POST /Chats/{id}/Messages to reply, GET /Contacts/{id} to fetch context, and POST /Contacts/Upsert to enrich the record. Complex conversations stay in Aurora and humans take them over from the same inbox.
On a new-message webhook, GET /Contacts/{id} for the sender, POST /Chats/{id}/Messages with a tailored reply, and POST /Contacts/Upsert to add the resolved tag.
Sales pipeline from conversations
Sales teams qualifying inbound enquiries on WhatsApp or Messenger want each qualified chat to become a tracked opportunity. /Chats/Search surfaces conversations matching a qualification keyword, /Contacts/{id} provides the lead record, and POST /Opportunities creates a pipeline entry tied to the contact. The pipeline stays current without a rep retyping notes into a separate CRM.
Search /Chats/Search for chats containing 'pricing' in the last 24 hours, and for each unique contact_id POST /Opportunities with a default stage and value of 0.
Contact and company sync to a primary CRM
Companies running HubSpot or Salesforce as the primary CRM still want messaging contacts mirrored. POST /Contacts/Upsert and GET /Companies keep Aurora's records aligned with the CRM, and webhooks push new contact and chat events outward. The result is one place to message and one place of record, kept consistent by the API.
List GET /Contacts updated in the last hour and call POST /Contacts/Upsert in the primary CRM with the same email and phone.
AI agent integration via Jentic
A chat-ops agent built on Jentic can reply across WhatsApp and Messenger without storing the X-API-Key in its prompt. The agent searches an intent like 'send a WhatsApp message via Aurora Inbox', Jentic returns the matching POST /Chats/{id}/Messages operation with its input schema, and execution uses the API key resolved from your Jentic One instance.
Use Jentic search 'send a message in an Aurora Inbox chat', load the schema for POST /Chats/{id}/Messages, and execute it with the chat_id and a templated reply body.
31 endpoints — jentic publishes the only available openapi specification for aurora platform api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/Chats
Create a chat
/Chats/{id}/Messages
Send a message in a chat
/Chats/Search
Search chats with filters
/Contacts
List contacts
/Contacts/Upsert
Upsert a contact by external ID
/Channels/WhatsAppBusiness
List WhatsApp Business channels
/Channels/WhatsAppCloudAPI
List WhatsApp Cloud API channels
/Channels/Messenger
List Messenger channels
/Chats
Create a chat
/Chats/{id}/Messages
Send a message in a chat
/Chats/Search
Search chats with filters
/Contacts
List contacts
/Contacts/Upsert
Upsert a contact by external ID
/Channels/WhatsAppBusiness
List WhatsApp Business channels
/Channels/WhatsAppCloudAPI
List WhatsApp Cloud API channels
/Channels/Messenger
List Messenger channels
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Aurora Platform API by hand means handling its X-API-Key header auth and picking a path across its chat, contact, and channel endpoints. Through Jentic you install once, import the Aurora Platform API from the API Directory, store the key once, and your agent calls it while Jentic injects the header.
Permission scoping
Aurora puts the chat id in the URL path (/Chats/{id}/Messages), so a rule can pin your agent to sending messages in one chat. You choose the operations it may call, so upserting contacts is not included unless you add it.
Credential isolation
Your Aurora X-API-Key value 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 'send a WhatsApp message', and Jentic returns the matching Aurora operation with its input schema so the agent picks /Chats/{id}/Messages or /Contacts/Upsert without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Aurora Platform API through Jentic.
Why is there no official OpenAPI spec for Aurora Platform API?
Aurora Inbox publishes developer documentation at developers.aurorainbox.com but does not distribute an OpenAPI file. Jentic generates and maintains this spec so that AI agents and developers can call Aurora Platform API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Aurora Platform API use?
The Aurora Platform API uses an API key passed in the X-API-Key header on every request. Keys are issued per workspace from the Aurora developer portal. Through Jentic the X-API-Key is held in the vault and injected at execution time.
Can I send WhatsApp messages with the Aurora Platform API?
Yes. Aurora connects to both WhatsApp Business and WhatsApp Cloud API channels. List the available channels via GET /Channels/WhatsAppBusiness or GET /Channels/WhatsAppCloudAPI, open a chat with POST /Chats, and send a message with POST /Chats/{id}/Messages.
What are the rate limits for the Aurora Platform API?
Aurora Inbox enforces a per-workspace rate limit that is not declared in the spec; the platform returns 429 with standard rate-limit headers when exceeded. WhatsApp tier limits also flow through, so high-volume sends should respect Meta's per-number quality-rating throttling.
How do I track new messaging-driven opportunities through Jentic?
Run jentic search 'create an Aurora Inbox opportunity', load the schema for POST /Opportunities, and execute it with the contact_id pulled from a chat. Jentic resolves the X-API-Key from the vault at execution time. With pip install jentic the call is one async invocation.
Is the Aurora Platform API free?
API access is included in Aurora Inbox's paid workspace plans. WhatsApp messaging itself is metered by Meta's conversation-based pricing, separate from the API call cost.
Can I limit what my agent is allowed to do with the Aurora Platform API?
Yes. Because you run your own self-hosted Jentic One instance, your own rules decide which Aurora operations and credentials the agent may use. Since Aurora carries the chat id in the URL path, such as POST /Chats/{id}/Messages, a rule can pin the agent to sending messages in a single chat. You pick the exact operations it may call, so upserting a contact via POST /Contacts/Upsert or creating a pipeline entry via POST /Opportunities stays off limits unless you explicitly allow it.
Know of an official OpenAPI document? Contribute it →
For Agents
Send and receive messages across WhatsApp, Messenger, and other channels, manage contacts, companies, opportunities, and webhooks via an X-API-Key authenticated REST API.
Use for: Send a WhatsApp message to a customer through Aurora Inbox, Open a new chat with a contact and assign it to a sales team, Search for every chat handled by a specific user this week, Upsert a contact so CRM and inbox stay in sync
Not supported: Does not handle voice calling, SMS-only carriers, or marketing campaign sends - use for Aurora Inbox multi-channel chat, contacts, and pipeline only.
Jentic publishes the only available OpenAPI specification for Aurora Platform API, keeping it validated and agent-ready. Aurora Inbox is a multi-channel messaging and CRM platform that unifies WhatsApp Business, WhatsApp Cloud API, Messenger, and other conversational channels into a single inbox. The Platform API exposes 31 endpoints across channels, chats, contacts, companies, opportunities, teams, users, chatbots, and webhooks, so an external CRM, ticketing tool, or AI agent can read inbound messages and write replies, manage contact records, and track sales opportunities tied to conversations.