AgenticOS
AgenticOS is a flexible and modular framework designed to help developers deploy and manage AI-driven workflows using agent-based systems. The framework is designed to be LLM-agnostic and core-tech switchable in the future, allowing developers to integrate their preferred agent systems seamlessly.
The goal is to provide a framework that integrates easily into your existing or planned infrastructure, giving you the flexibility to focus on AI task execution without complex setups.
Geting started
Installing the prerequisites
pipx
This is currently a recomended way to install comamnds that are available accros your systems like build backends or other code generators. Please follow instructions for your operating system: https://pipx.pypa.io/stable/installation/
hatch
This build backend is required by crew AI. You can install it with pipx:
pipx install hatch
For other installation options please check the official instructions: https://python-poetry.org/docs/#ci-recommendations
CrewAI
Please install CrewAI using the pipx:
pipx install crewai
⚠️ Please make sure that you update CrewAI before every use.
Creating a new project
- Create a new CrewAI crew. If you are installing agenticos alongside exising CrewAI project please go to point 3.
crewai create crew new_crew
- Generate venv and install dependencies:
cd new_crew
hatch shell
- Install agenticos package using poetry:
pip install agenticos
- Add agenticos to
pyproject.toml. Use the following command to find out which version do you need.
pip freeze | grep agenticos
- Generate agentic scaffold files:
agentic init
It will generate following files in your project:
[app_root]
|-src
|-agentic
|-agentic_node.py
|-agentic_config.py
⚠️ This configuration should work with out-of the box crewai project. If you made any changes to project structure you will have to update
agentic_config.pyfile.
Running
Currentic agentic node may be run only as a standalone HTTP server. Production fastapi mode:
agentic run
or dev fastapi mode:
agentic run --dev
Config via ENV VARS
Order of priority CLI ARGS > ENV_VARS > DEFAULTS. Current env vars with defaults:
AUTH_TOKEN: str = ""
REGISTRY_URL: str = "ws://localhost:8080"
NODE_MODE: str = "httpserver"
HTTP_PORT: int = 8000
AGENTIC_CONFIG_PATH: str = "src/agentic/agentic_config.py"
HTTP_HEALTHCHECK : bool = False
Metadata
Release files for agenticos 0.0.3.156160
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 |
|---|---|---|---|---|
| agenticos-0.0.3.156160.tar.gz | 15.4 kB | Without provenance | Details for agenticos-0.0.3.156160.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agenticos-0.0.3.156160-py3-none-any.whl | Python 3 | none | any | Details for agenticos-0.0.3.156160-py3-none-any.whl |
Total release size: 35.5 kB
Release files / agenticos-0.0.3.156160.tar.gz
| Download URL | agenticos-0.0.3.156160.tar.gz |
|---|---|
| Size | 15.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1902c6daa2bcb9d09516d8d4e2e31d1098d71ef35d386bc7d55e860080e133a0
|
|
BLAKE2b-256 checksum How to use checksums |
aad8121a6420016d00712f1100dd224bfc16b0d3a82387c62ee49a324727f5c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.10.12 Linux/6.5.0-1022-aws
|
Release files / agenticos-0.0.3.156160-py3-none-any.whl
| Download URL | agenticos-0.0.3.156160-py3-none-any.whl |
|---|---|
| Size | 20.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
899ca91d81b00a50abc5640509aab3d561c115230b901c220af69c0e55e038c6
|
|
BLAKE2b-256 checksum How to use checksums |
feb82f5e0246d1c94cc0c0231dc6dd20f382c173067c2b459eeece8ddc1ed752
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.10.12 Linux/6.5.0-1022-aws
|
Security for agenticos 0.0.3.156160
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.