Telegram Reasoning Agent

ReasoningTools + DuckDuckGo search on Telegram

Code

reasoning_agent.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os.app import AgentOS
from agno.os.interfaces.telegram import Telegram
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.reasoning import ReasoningTools

agent_db = SqliteDb(db_file="tmp/persistent_memory.db")

reasoning_agent = Agent(
    name="Reasoning Research Agent",
    model=OpenAIChat(id="gpt-5.2"),
    db=agent_db,
    tools=[
        ReasoningTools(add_instructions=True),
        DuckDuckGoTools(),
    ],
    instructions="Use tables to display data. When you use thinking tools, keep the thinking brief.",
    add_datetime_to_context=True,
    markdown=True,
)


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

if __name__ == "__main__":
    agent_os.serve(app="reasoning_agent:app", reload=True)

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Set Environment Variables

   export TELEGRAM_TOKEN=your-bot-token-from-botfather
   export OPENAI_API_KEY=your-openai-api-key
   export APP_ENV=development
   
3. Install dependencies

   uv pip install -U "agno[telegram]" duckduckgo-search
   
4. Run Example

   python reasoning_agent.py
   

Key Features

• Chain-of-Thought Reasoning: ReasoningTools enables structured thinking for complex queries
• Web Search: DuckDuckGo integration for up-to-date information retrieval
• Data Presentation: Uses tables to display structured data
• Persistent Memory: SQLite database for session storage