AACP coordination layer for AutoGen multi-agent workflows
Project description
aacp-autogen
AACP coordination layer for AutoGen multi-agent workflows.
AutoGen's GroupChat model makes AACP particularly valuable. Without AACP, agents exchange full conversational messages -- preamble, content, clarifying questions, acknowledgements. AACP replaces all of that with typed, deterministic packets.
Install
pip install aacp-autogen
Requires Python >=3.11, <3.12 (pyautogen 0.2.x constraint).
Quick start
from aacp_autogen.orchestrator import AACPAutoGenOrchestrator
orch = AACPAutoGenOrchestrator(model="gpt-4o-mini")
result = orch.run_workflow("payroll", period="2026-03")
print(result.summary())
Comparison demo
python3 examples/comparison.py --mock
Links
- Protocol: https://aacp.dev
- Python SDK: https://github.com/MackayAndrew/aacp
- LangChain: https://github.com/MackayAndrew/aacp-langchain
- CrewAI: https://github.com/MackayAndrew/aacp-crewai
- IETF Draft: https://datatracker.ietf.org/doc/draft-mackay-aacp/
Licence
MIT
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file aacp_autogen-0.1.0.tar.gz.
File metadata
- Download URL: aacp_autogen-0.1.0.tar.gz
- Upload date:
- Size: 12.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
18a9bc9c0703fb9282bf07c25e3659cb0f27380cd2da536846159c130037c05c
|
|
| MD5 |
3656fb85973bc73ff5d57c95b40d6b25
|
|
| BLAKE2b-256 |
adbe61d9d583e79085e43c6a9f036088f480e9402a9b1845e170d68442e06737
|
File details
Details for the file aacp_autogen-0.1.0-py3-none-any.whl.
File metadata
- Download URL: aacp_autogen-0.1.0-py3-none-any.whl
- Upload date:
- Size: 15.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
20761df56262eea580847a2cbdc146d15165329d08eb628edc41e4bc133d6fee
|
|
| MD5 |
8513d9c0f6a1561566a2c8c59de6f655
|
|
| BLAKE2b-256 |
1a3238d517ed8040028ce3c86f1637bf00d6bf579068adda1e446667ec27c956
|
