v2.5.10

The new Telegram interface mounts webhook endpoints directly on AgentOS, turning any agent, team, or workflow into a fully functional Telegram bot. Inbound messages — text, photos, voice notes, audio, video, documents, stickers, and animations — are handled natively and passed to the agent as structured inputs. Responses stream back in real time with live message edits, throttled to stay within Telegram's rate limits, so users see output as it is generated rather than waiting for a complete reply.

‍

Create an agent, expose it with the Telegram interface, and serve via AgentOS:
‍

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.google import Gemini
from agno.os.app import AgentOS
from agno.os.interfaces.telegram import Telegram

agent_db = SqliteDb(session_table="telegram_sessions", db_file="tmp/telegram_basic.db")

telegram_agent = Agent(
    name="Telegram Bot",
    model=Gemini(id="gemini-2.5-pro"),
    db=agent_db,
    instructions=[
        "You are a helpful assistant on Telegram.",
        "Keep responses concise and friendly.",
    ],
    add_history_to_context=True,
    num_history_runs=3,
    add_datetime_to_context=True,
    markdown=True,
)

agent_os = AgentOS(
    agents=[telegram_agent],
    interfaces=[Telegram(agent=telegram_agent)],
)
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="basic:app", port=7777, reload=True)

‍


See the Telegram docs for more.