AgentFleet
A Python package for managing AI agents and chatrooms that work with LLM-based capabilities.
Installation
pip install agentfleet
Usage
from agentfleet import Agent, Chatroom, create_chatroom
# Example: Create an agent
from langchain_openai import ChatOpenAI
llm = ChatOpenAI()
agent = Agent(name="Assistant", llm=llm, sys_prompt="You are a helpful assistant")
# Example: Set up a chatroom
chatroom = Chatroom(llm=llm, agents=[agent], current_agent=agent)
Using Custom Tools
from agentfleet import create_chatroom
from langchain_core.tools import tool
# Define your custom tool functions
@tool
def lookup_data(query: str) -> str:
"""Look up data from a database."""
# Implementation...
return f"Data for {query}"
@tool
def process_request(request_id: str) -> str:
"""Process a request with the given ID."""
# Implementation...
return f"Processed request {request_id}"
# Create a dictionary mapping tool names to functions
tool_dict = {
'lookup_data': lookup_data,
'process_request': process_request
}
# Create a chatroom with tool dictionary
chatroom_config = {
"states": [...],
"agents": [
{
"name": "support_agent",
"sys_prompt": "You are a support agent...",
"util_tools": ["lookup_data", "process_request"],
"transfer_tools": []
}
],
"initial_agent": "support_agent"
}
chatroom = create_chatroom(chatroom_config, llm, tool_dict=tool_dict)
Features
- Create AI agents with different capabilities
- Build chatrooms with multiple specialized agents
- Transfer conversation control between agents
- Maintain conversation state across interactions
- Pass custom tools to agents via tool dictionary
License
MIT License
Copyright (c) 2025 Wei Zhou
Contributing
Individual Contributor: Wei Zhou
We welcome contributions! Please review our contribution guidelines for details on our code of conduct, and the process for submitting pull requests.
Metadata
Release files for agentfleet 0.1.4
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 | Actions |
|---|---|---|---|---|
| agentfleet-0.1.4.tar.gz | 6.6 kB | Without provenance | Details for agentfleet-0.1.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentfleet-0.1.4-py3-none-any.whl | Python 3 | none | any | Details for agentfleet-0.1.4-py3-none-any.whl |
Total release size: 13.6 kB
Release files / agentfleet-0.1.4.tar.gz
| Download URL | agentfleet-0.1.4.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
50ef9b128a82cb140036f5cdb42fcc87939604825850883855ca6a191db1093b
|
|
BLAKE2b-256 checksum How to use checksums |
f213970fd95a65079f91f2d550202a9da14d74aa628be191854997e14f5ac6df
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Release files / agentfleet-0.1.4-py3-none-any.whl
| Download URL | agentfleet-0.1.4-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e6f562241785581e384307e79f399819be3ea848ef72c62cc1d85ed84c9b1c91
|
|
BLAKE2b-256 checksum How to use checksums |
f06518f1fbe47df3e30bb74e1c54e5780ae2fb685a9fefccc8817e9e2fba1aa5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Security for agentfleet 0.1.4
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.