Skip to main content

TeamGen AI, developed by Eliran Wong, automates the creation of AI agent teams to address user requests.

Project description

# TeamGen AI

TeamGen AI, developed by [Eliran Wong](https://github.com/eliranwong), automates the creation of AI agent teams to address user requests.

# How does it work?

Upon receiving a user request, TeamGen AI generates a team of AI agents, each with a distinct role. They were then assigned in turns to work collaborately in a group discussion. During each turn of the group discussion, TeamGen AI evaluates the progress and assigns the most suitable agent to contribute. Once all agents have provided their expertise and the request is fully addressed, TeamGen AI engages the final answer writer to deliver the response to the user.

# Supported AI Backends

The following AI Backends are supported and tested:

anthropic, azure, genai, googleai, groq, llamacppserver, mistral, ollama, openai, xai

Compare at: https://github.com/eliranwong/teamgenai/tree/main/examples/example_02

# Latest Features

Read https://github.com/eliranwong/teamgenai/blob/main/latest.md

# Requirements

To run TeamGen AI, you need to install and setup [ToolMate AI](https://github.com/eliranwong/toolmate) (version 0.6.34 or later) FIRST!

To install:

> pip install –upgrade toolmate

To install on Android Termux:

> pip install –upgrade toolmate_lite

To setup ToolMate AI:

> tmsetup -m

Select AI a backend and a model. Enter API keys if the selected backend requires.

Note: We are using toolmate as a library to quicken the initial development of this project. We may consider removing this requirement as this project grow.

# Installation

> pip install teamgenai

We recommend creating a virtual environment first, e.g.

` python3 -m venv tgai source tgai/bin/activate pip install --upgrade toolmate teamgenai # setup ToolMate AI tmsetup -m `

Install toolmate_lite instead of toolmate on Android Termux, e.g.

` python3 -m venv tgai source tgai/bin/activate pip install --upgrade toolmate_lite teamgenai # setup ToolMate AI tmsetup -m `

# Run TeamGen AI

Run TeamGen AI with command: tgai

For CLI options run:

> tgai -h

To enter your request in interactive mode:

> tgai

To run with a single command, e.g.

> tgai Write a Christmas song

Result of this example: https://github.com/eliranwong/teamgenai/blob/main/examples/example_01.md

> tgai Write a comprehensive introduction to the book of Daniel in the bible

Results of this example, comparing different AI backends: https://github.com/eliranwong/teamgenai/tree/main/examples/example_02

# Development Road Map

  1. Creat an initial version that support group discussion between AI agents (Done! version 0.0.2)

  2. Support backup and reuse of generated agent configurations (Done! version 0.0.2)

  3. Test all the [AI backends supported by ToolMate AI](https://github.com/eliranwong/toolmate#ai-backends-and-models) ([Done!](https://github.com/eliranwong/teamgenai/tree/main/examples/example_02))

  4. Support specifying different AI backends or models for running agent creation, assignment and responses

  5. Support customisation of core system messages that run TeamGen AI (Done! version 0.0.3)

  6. Support code generation and task execution

  7. Integrate ToolMate AI tools and plugins

  8. May remove dependency on ToolMate AI

  9. More …

Welcome further suggestions!

# Welcome Contributions

You are welcome to make contributions to this project by:

  • joining the development collaboratively

  • donations to show support and invest for the future

Support link: https://www.paypal.me/toolmate

Please kindly report of any issues at https://github.com/eliranwong/teamgenai/issues

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

teamgenai-0.0.10.tar.gz (22.0 kB view details)

Uploaded Source

Built Distribution

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

teamgenai-0.0.10-py3-none-any.whl (23.2 kB view details)

Uploaded Python 3

File details

Details for the file teamgenai-0.0.10.tar.gz.

File metadata

  • Download URL: teamgenai-0.0.10.tar.gz
  • Upload date:
  • Size: 22.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.12

File hashes

Hashes for teamgenai-0.0.10.tar.gz
Algorithm Hash digest
SHA256 926545b0fdae6d5ff752e3bb1a6b08d313c680652263d2c81414e9d10d5ec07d
MD5 5430b1b282f93b8364e58e9b8b0054e9
BLAKE2b-256 91e10bb68a092b35c5d3f3fac5264598b1b9684af5b56ff0e2ee84d3a3a4ef31

See more details on using hashes here.

File details

Details for the file teamgenai-0.0.10-py3-none-any.whl.

File metadata

  • Download URL: teamgenai-0.0.10-py3-none-any.whl
  • Upload date:
  • Size: 23.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.10.12

File hashes

Hashes for teamgenai-0.0.10-py3-none-any.whl
Algorithm Hash digest
SHA256 0a8aa66d9ed6b32cc89b4a15dd92abd61950c4cb8e92a9bb6c532d6ec9f1c141
MD5 25396809f7bf0a137e77041af052f1b4
BLAKE2b-256 7576b24a9a3e10c0b6f5190c037cca0ca54fe3b9e297a0ad0567a0f41ffd2bed

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