django-agentkore
A Django extension for scaffolding and managing LLM-based agents in your Django projects.
Features
- Django management command for agent scaffolding (
startagent) - Base agent classes and utilities
- Agent auto-discovery in Django projects
- Easily integrate AI agents into your Django applications
Installation
pip install agentkore
Using uv
You can also install using uv, a fast Python package installer and resolver:
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create and activate a virtual environment
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install agentkore
uv pip install agentkore
Setting up in your Django project
- Add
agentkoreto yourINSTALLED_APPSin your Django settings:
INSTALLED_APPS = [
# ... other apps
'agentkore',
]
- Run the
startagentcommand to create a new agent:
python manage.py startagent myagent
This will create the following structure:
agents/
myagent/
__init__.py
agent.py
prompt_templates/
base.txt
tests/
__init__.py
test_myagent.py
Using your agent
from agents.myagent import MyagentAgent
# Create an instance of your agent
agent = MyagentAgent()
# Process a user prompt
response = agent.run("What's the weather like today?")
Auto-discovering agents
The AgentRegistry class can automatically discover all agents in your project:
from agentkore.kore import discover_agents
# Discover all agents in the 'agents' directory
agents = discover_agents()
# Get a list of all available agent names
agent_names = list(agents.keys())
Creating Custom Agents
Extend the BaseAgent class to implement your own AI agents:
from agentkore.kore import BaseAgent
import openai
class WeatherAgent(BaseAgent):
def run(self, prompt, context=None):
# Use OpenAI to process weather queries
response = openai.ChatCompletion.create(
model="gpt-4",
messages=[
{"role": "system", "content": "You are a weather assistant."},
{"role": "user", "content": prompt}
]
)
return response.choices[0].message.content
Metadata
Release files for django-agentkore 0.1.0
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 | Actions |
|---|---|---|---|---|
| django_agentkore-0.1.0.tar.gz | 7.1 kB | Without provenance | Details for django_agentkore-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| django_agentkore-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for django_agentkore-0.1.0-py3-none-any.whl |
Total release size: 14.3 kB
Release files / django_agentkore-0.1.0.tar.gz
| Download URL | django_agentkore-0.1.0.tar.gz |
|---|---|
| Size | 7.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9d44a9597520c4bc04e68f5c193e1a363eef4444303764dc1afb867e923bfadd
|
|
BLAKE2b-256 checksum How to use checksums |
7203e297bd956c87901caa8be5fa26b46ff68dd4c07f5219c021c5ff7c98cfbf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.5
|
Release files / django_agentkore-0.1.0-py3-none-any.whl
| Download URL | django_agentkore-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bd1d09cc56209c5434a3806388fe1ed7af0879c138e7f6d3ed94504b46f3da82
|
|
BLAKE2b-256 checksum How to use checksums |
a5a33a34249d5ac7b5762c6267ff6b8c17306b2e2de33d23b116c173521f548b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.5
|
Security for django-agentkore 0.1.0
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.