Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the TG alerter, 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%2Fswaggerhub.rjericho%2Ftg-alerter" | 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%2Fswaggerhub.rjericho%2Ftg-alerter" | 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 TG alerter API.
Send message to user or group
Add a new group
Get all groups
Delete user to group relation
GET STARTED
For Agents
Programmatically send message to user or group, add a new group. Covers 11 operations.
Use for: I need to send message to user or group, I want to add a new group, Search for all groups, Find all add user to group
Not supported: Does not handle payments, communications, or crm - use for developer tools only.
This is a sample telegram alerter. The API exposes 11 endpoints.
Find user by ID
Patterns agents use TG alerter API for, with concrete tasks.
★ Developer Tools Operations
Use the TG alerter to perform developer tools operations programmatically. The API provides 11 endpoints covering core functionality including send message to user or group, add a new group, get all groups.
Call POST /alert to send message to user or group
Automated users Management
Automate users operations by combining multiple TG alerter endpoints. Agents can add a new group and then get all groups in a single workflow.
Call POST /api/groups to add a new group, then verify the result
AI Agent Integration via Jentic
AI agents discover and call TG alerter endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually.
Search Jentic for 'send message to user or group', load the operation schema, and execute with Jentic-managed credentials
11 endpoints — this is a sample telegram alerter.
METHOD
PATH
DESCRIPTION
/alert
Send message to user or group
/api/groups
Add a new group
/api/groups
Get all groups
/api/groups/useradd
Add user to group
/api/groups/userdel
Delete user to group relation
/api/groups/{groupId}
Find user by ID
/api/groups/{groupId}
Deletes a group
/api/users
Add a new user
/alert
Send message to user or group
/api/groups
Add a new group
/api/groups
Get all groups
/api/groups/useradd
Add user to group
/api/groups/userdel
Delete user to group relation
What agents get from Jentic-routed access to this vendor.
Setup
Wiring TG alerter by hand means standing up its base host and handling requests and retries yourself, even though it ships no auth scheme. Through Jentic you install once, import TG alerter from the API Directory, store any connection details once, and your agent calls it.
Permission scoping
TG alerter puts the group id in the URL path (/api/groups/{groupId}), so a rule can pin your agent to one group: it can read that group and nothing else. You choose the operations it may call, so writes like adding or removing users or deleting a group are not included unless you add them.
Credential isolation
Any TG alerter connection detail 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 an alert message' or 'list groups', and Jentic returns the matching TG alerter 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.
Github
Alternative developer tools API
Choose Github when you need a different approach to developer tools operations
Specific to using TG alerter API through Jentic.
What authentication does the TG alerter use?
The TG alerter uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I send message to user or group with the TG alerter?
Yes. Use the POST /alert endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the TG alerter?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I send message to user or group through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'send message to user or group'. Jentic returns the matching TG alerter operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the TG alerter have?
The TG alerter exposes 11 endpoints covering users, groups, alert operations.
Can I limit what my agent is allowed to do with the TG alerter?
Yes. Because you run Jentic One yourself and self-host the execution layer, your own rules decide which TG alerter operations and connection details the agent may use. Since the group id sits in the URL path (/api/groups/{groupId}), you can pin the agent to a single group and let it only read that group with GET /api/groups/{groupId}. Write operations such as sending alerts via POST /alert, adding or removing members via /api/groups/useradd and /api/groups/userdel, or deleting a group are excluded until you explicitly allow them.
/api/groups/{groupId}
Find user by ID
/api/groups/{groupId}
Deletes a group
/api/users
Add a new user