A developer library for LLM-based agents
Project description
agentkore
A Python library for building LLM-based agents.
Features
- Simple agent scaffolding
- Pluggable “tool” interface
- Built-in OpenAI / LangChain adapters
Installation
pip install agentkore
Using uv
You can also install and bootstrap the package 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
# For development installation with all dependencies
git clone https://github.com/shipkode/agentkore.git
cd agentkore
uv pip install -e ".[dev]"
# Building the package with uv
uv pip install build
uv run -m build
# This will create distribution packages in the dist/ directory:
# - A source distribution (.tar.gz)
# - A wheel distribution (.whl)
# Publishing to PyPI
uv pip install twine
# First, create an account on TestPyPI (https://test.pypi.org/account/register/)
# and PyPI (https://pypi.org/account/register/) if you don't have one
# Generate an API token:
# - For TestPyPI: https://test.pypi.org/manage/account/token/
# - For PyPI: https://pypi.org/manage/account/token/
# Create or edit ~/.pypirc file with your tokens:
# [testpypi]
# username = __token__
# password = your-test-pypi-token
#
# [pypi]
# username = __token__
# password = your-pypi-token
# Upload to TestPyPI first to test
uv run -m twine upload --repository testpypi dist/*
# Once tested, upload to the real PyPI
# uv run -m twine upload dist/*
# You can also specify credentials directly if needed
# uv run -m twine upload --repository testpypi --username __token__ --password your-token dist/*
Quickstart
from agentkore import Agent
agent = Agent(name="hello-world")
response = agent.run("Say hello to the world")
print(response)
Contributing
- Fork the repo
- Create a feature branch (git checkout -b feat/…)
- Commit and push
- Open a PR
Project details
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
agentkore-0.1.0.tar.gz
(3.4 kB
view details)
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 agentkore-0.1.0.tar.gz.
File metadata
- Download URL: agentkore-0.1.0.tar.gz
- Upload date:
- Size: 3.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b2eacab7cf1b52a5e8ce11784618d1d66743046bf71f2e45f7b69f88a74fc01a
|
|
| MD5 |
e97a0ba3d589d1416fd6e78cdf1f9834
|
|
| BLAKE2b-256 |
7fa8f4bbd549758daee8d49ebc30394edf049722d19f57259264fb9cd8eebf88
|
File details
Details for the file agentkore-0.1.0-py3-none-any.whl.
File metadata
- Download URL: agentkore-0.1.0-py3-none-any.whl
- Upload date:
- Size: 4.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5532b1876f464afd46a6675487e5a7d7cc4c5a38cbc3a53544782dcf93e99d2a
|
|
| MD5 |
c2d0371be99cadd3ffd98e94c6442363
|
|
| BLAKE2b-256 |
f5a98633ea8d13002e01fc6491dee545a5b549deb3eeed729654df47b179999a
|