Optional agent framework adapters for PraisonAI (CrewAI, AutoGen, extensions)
Project description
PraisonAI Frameworks
Optional agent framework adapters for PraisonAI.
Implements the praisonai.framework_adapters entry-point group so YAML framework: values
(crewai, autogen, …) resolve without bloating the core SDK or wrapper wheel.
Install
# Native PraisonAI only (no third-party frameworks)
pip install praisonaiagents praisonai
# CrewAI backend
pip install praisonai-frameworks[crewai]
# AutoGen v0.2 backend
pip install praisonai-frameworks[autogen]
# LangGraph backend
pip install praisonai-frameworks[langgraph]
# OpenAI Agents SDK backend
pip install praisonai-frameworks[openai-agents]
# Agno backend
pip install praisonai-frameworks[agno]
# Google ADK backend
pip install praisonai-frameworks[google-adk]
# AutoGen v0.4 backend (autogen-agentchat / autogen-ext)
pip install praisonai-frameworks[autogen-v4]
Selecting an AutoGen version
Use framework: autogen and set AUTOGEN_VERSION to choose a backend:
AUTOGEN_VERSION |
Backend |
|---|---|
v0.2 |
AutoGen v0.2 (autogen) |
v0.4 |
AutoGen v0.4 (autogen-agentchat) |
ag2 |
AG2 fork |
auto (default) |
First available: v0.2 → v0.4 → ag2 |
Usage
# agents.yaml
framework: crewai
topic: Research AI trends
roles:
researcher:
role: Research Analyst
goal: Find accurate information
backstory: Expert researcher
tasks:
research:
agent: researcher
description: Research {topic}
expected_output: A concise summary
praisonai run agents.yaml
Architecture
- Depends on
praisonaiagentsonly (protocol + base helpers inpraisonaiagents.frameworks) - Registers adapters via setuptools entry points — no wrapper import required
- Lazy-imports CrewAI / AutoGen inside
run()only
Adding a framework
See examples/third_party_adapter/ and docs/adding-a-framework.md.
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
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 praisonai_frameworks-0.1.7.tar.gz.
File metadata
- Download URL: praisonai_frameworks-0.1.7.tar.gz
- Upload date:
- Size: 56.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
54a48c4a8c28503905bad212b7c0027ac9e5f651c94586f81681fd137bfcf753
|
|
| MD5 |
79c80ac4af14d473a04f6c30a9fb9c7c
|
|
| BLAKE2b-256 |
52ec9d696cfc22f6c931ca256618f393bdef7f90397b1d7a32f07117dfa3c699
|
File details
Details for the file praisonai_frameworks-0.1.7-py3-none-any.whl.
File metadata
- Download URL: praisonai_frameworks-0.1.7-py3-none-any.whl
- Upload date:
- Size: 31.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1acd6ebcc1495fc58c65217bd24113c728305b6805e83173c8a03f85ac54e8d8
|
|
| MD5 |
e4f22fdb990d2bacba84016b5795e98a
|
|
| BLAKE2b-256 |
2d8b30524bf35198076e3c1555649c5af2147b6952fcf3ed236f5a0cdff1ad54
|