How It Works
Prepare Code
Add a Flask /run endpoint to call your agent and a requirements.txt for dependencies.
from flask import Flask, request, jsonify
import os
app = Flask(__name__)
@app.route("/run", methods=["POST"])
def run_agent_endpoint():
data = request.get_json() # Pass parameters to the agent
env_vars = os.environ # Access environment variables
agent_output = my_agent_logic(data, env_vars)
return jsonify(agent_output)
def my_agent_logic(params, env_vars):
# Print statements are automatically capture by Itura
print(f"{len(params)} parameters and {len(env_vars)} env variables received")
# TODO: Implement your agent logic here using your favorite stack
return {"message": "Agent executed successfully!", "output": "Agent output"}Connect GitHub
Link your repository. Itura packages and deploys the code.
Add Environment Variables
Configure secrets (like API keys) via the Itura UI.
Deployment Complete! 🎉
That's it! Itura handles the rest. Your agent is automatically deployed to a unique, secure URL (like https://your-agent.agent.itura.ai) with an API key. You can monitor execution history, logs, and status directly in the Itura UI. New commits to your connected repository trigger automatic re-deployments.
curl -X POST https://your-agent-name.agent.itura.ai/run \
-H "Authorization: Bearer <your_api_key>" \
-H "Content-Type: application/json" \
-d '{"input": "Data for your agent"}'Use Cases
Automation Agents
Automate data entry, generate reports, trigger complex workflows, or send personalized notifications based on real-time events.
Content Generation
Deploy agents that draft emails, summarize text, generate code snippets, or transform content for different audiences.
Information Gathering
Build agents that monitor websites, extract specific data from web pages, or perform targeted research tasks.
Key Features
Flexible
Supports any Python framework, library, or LLM via the Flask `/run` endpoint.
Agent-Focused
Manages Python dependencies, secure environment variable injection, serverless execution suitable for agent tasks.
Serverless & Scalable
No server management; scales automatically based on workload.
Secure
Isolated containerized execution environment; encrypted communication.
Automatic Updates
Integrates with GitHub for continuous deployment.
Predictable Costs
Pay a flat fee covering all costs (compute, log storage, bandwidth, etc.)
Built for humans
AI/ML Developers & Engineers
Focus on building powerful agents with your favorite Python tools; let Itura handle deployment, scaling, and monitoring.
Startups
Launch and iterate on your AI-powered products faster. Itura's serverless model scales with your needs and keeps costs predictable.
Python Developers
Easily bring your agentic application ideas to life. If you know how to code the most basic Flask application, you can deploy on Itura in minutes.
Technical Overview
Deployment
Docker containers on a serverless platform (AWS/GCP based).
Runtimes
Python 3.9, 3.10, 3.11, 3.12, 3.13.
Resources
1GB RAM, 10 GB temporary storage per invocation.
Max Execution Time
10 minutes per invocation.
Code Size Limit
1 GB per agent.
Logging
Print statements and logs are automatically captured; viewable in the Itura UI.