Skip to main content

A framework for building and running AI agents

Project description

AgentHub Python SDK

A lightweight Python framework for building and running AI agents in simulation environments.

Installation

pip install agenthub-py

Quick Start

from agenthub import AgentRunner
from typing import Any, Dict, List

class MyAgent(AgentRunner):
    def run(self, input_data: Dict[str, Any] | List[Dict[str, Any]]) -> Dict[str, Any]:
        # Preprocess your input_data here and generate the agent response
        response = self.generate_agent_result(input_data)
        # Return the result in the desired format
        result = {"status": "success", "data": response}
        return result

# Create and use your agent
agent = MyAgent()
response = agent.run({"message": "Hello, Agent!"})
print(response)

Requirements

  • Python 3.8 or higher

License

MIT

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agenthub_py-0.1.1.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agenthub_py-0.1.1-py3-none-any.whl (3.1 kB view details)

Uploaded Python 3

File details

Details for the file agenthub_py-0.1.1.tar.gz.

File metadata

  • Download URL: agenthub_py-0.1.1.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for agenthub_py-0.1.1.tar.gz
Algorithm Hash digest
SHA256 2b590030d6f3e9363f8f3bb78d03a52d2850a9205b5ebfc60dfa2804cb7aef85
MD5 2188ae55f46f8705cfd0a102e7b571db
BLAKE2b-256 ca4d35b0e30a3f27144c91dc0e477371e91094bb2e698debd1b8944642f85878

See more details on using hashes here.

File details

Details for the file agenthub_py-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: agenthub_py-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 3.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.5

File hashes

Hashes for agenthub_py-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 78f81b7ef61fd422fff7cf36c95cec47b8bbf7573cb9ce2ba1f2b67c452f04a8
MD5 74258ba78b1b41a2338eae7b0764a6c4
BLAKE2b-256 f6094ff1a3e82d482c4a2767189dce84c34806ca244da253657cf8de759f6dd4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page