# TeamGen AI
TeamGen AI, developed by [Eliran Wong](https://github.com/eliranwong), automates the creation of AI agent teams to address user requests.
## Version 2.0
Version 2.0+ is completely re-written, built-on [AgentMake AI](https://github.com/eliranwong/agentmake) SDK.
# 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.
# Agentic Workflow
<img width=”832” alt=”Image” src=”https://github.com/user-attachments/assets/cf27cf97-ea7a-42bd-a050-3663064dc07d” />
# AI Backends and Configurations
ToolMate AI uses [AgentMake AI](https://github.com/eliranwong/agentmake) configurations. The default AI backend is Ollama, but you can easily edit the default backend and other configurations. To configure, run:
> ai -ec
# Installation
> pip install teamgenai
Setting up a virtual environment is recommended, e.g.
` python3 -m venv tgai source tgai/bin/activate pip install --upgrade teamgenai # setup ai -m `
Install extra package genai to support backend Vertex AI via google-genai library:
` python3 -m venv tgai source tgai/bin/activate pip install --upgrade "teamgenai[genai]" # setup ai -m `
# Run TeamGen AI
Run TeamGen AI with command teamgenai or tgai.
Remarks: tgai is an alias to teamgenai.
For CLI options run:
> tgai -h
To enter your request in editor 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
# 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
Metadata
Release files for teamgenai 2.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| teamgenai-2.0.0.tar.gz | 17.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| teamgenai-2.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 35.1 kB
Release files / teamgenai-2.0.0.tar.gz
| Download URL | teamgenai-2.0.0.tar.gz |
|---|---|
| Size | 17.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
61f6c45e9b9c1701707e5bb88c88aca452cfbb8ef0e5495bd93a56e8ae4c0810
|
|
BLAKE2b-256 checksum How to use checksums |
6a9d3ee3db5eaead50fd58bc5147ce5236f34226ff407ef02341fafdd7b601f2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.9
|
Release files / teamgenai-2.0.0-py3-none-any.whl
| Download URL | teamgenai-2.0.0-py3-none-any.whl |
|---|---|
| Size | 18.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b2f90e93e939d8c8f5d25d1fa400eb7aabb3656969b92c14c53d7bea42cd6521
|
|
BLAKE2b-256 checksum How to use checksums |
e9bf264dd59489611d684c037e509a48cdf6192873e993ae86693349e97981bc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.9
|
Security for teamgenai 2.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.