Skip to main content
Quarantined

This project has been quarantined by PyPI admins. It cannot be installed or modified until a security review is complete.

CoreAgent

Simplest Agent Framework

| Documentation | Discord |


CoreAgent is a lightweight and intuitive framework designed to make building intelligent agents straightforward. Focusing on simplicity, CoreAgent allows you to quickly integrate language models with custom tools to create powerful and versatile applications.

Key Features

  • Universal: Both coding, chatting, one Agent class handles them all!
  • Simplicity First: Ease of use and minimal boilerplate.
  • Sharable Tool States: Share the same tool instances states across multiple agents.
  • Built-in Tools: Lots of built-in tools to get you started fast!

Installation

To install CoreAgent, simply use pip:

pip install coreagent

Getting Started

Here's a basic example demonstrating how to use CoreAgent:

from coreagent import Agent
import urllib.request
import json

class IPTool:
  def get_my_ip(self) -> str:
    j = json.loads(urllib.request.urlopen("https://api.ipify.org/?format=json").read().decode())
    return j['ip']

s = Agent()
s.register_tool(IPTool())

s.chat("What's my IP address? ")

Registering Tools

CoreAgent makes it easy to integrate your own custom functionalities as tools. To register a tool, you simply need to:

  1. Define a Python class for your tool.
  2. Implement the methods you want to expose to the agent. Use docstrings to provide descriptions for your methods. These descriptions can be used by the agent to understand how to use the tool.
  3. Instantiate your tool class.
  4. Register the instance with the ChatSession using the register_tool() method.

Refer to the example above for a practical demonstration of tool registration.

Roadmap

  • Basic universal agent framework.
  • Remove guided_grammar restriction, allow general LLM usage (DeepSeek API, GPT3.5/4/4o API, Qwen API, etc. )
  • More intuitive simplified examples, alowing hands-on try-outs.
  • RAG-based memory module.

Contributing

Contributions to CoreAgent are welcome! If you have ideas for improvements, bug fixes, or new features, please feel free to open an issue or submit a pull request.

License

Brought to you by Shanghai Glacies Technologies Co,. LTD.
GNU Lesser General Public License v3.0 https://www.gnu.org/licenses/lgpl-3.0.en.html

Star History

Star History Chart

Metadata

Release files for coreagent 0.1.1a0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for coreagent 0.1.1a0
File Size Uploaded Provenance
coreagent-0.1.1a0.tar.gz 15.8 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for coreagent 0.1.1a0
File Interpreter ABI Platform
coreagent-0.1.1a0-py2.py3-none-any.whl Python 2, Python 3 none any Details

Total release size: 34.3 kB

Release files / coreagent-0.1.1a0.tar.gz

Download URL coreagent-0.1.1a0.tar.gz
Size 15.8 kB
Tags Source
SHA-256 checksum
How to use checksums
633b1c348cfc50c4025778700df7261343a441f888ffdde48ab677b0e63feaad
BLAKE2b-256 checksum
How to use checksums
4b6038a9ea07dd5f213eb9d7f1154a9ec2c6a38ef4229bbb69f8b83518742775
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 3, 2025.

Transparency log

Release files / coreagent-0.1.1a0-py2.py3-none-any.whl

Download URL coreagent-0.1.1a0-py2.py3-none-any.whl
Size 18.5 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
d3373cfa75679958396328e63ef8414de3655892f14594d50f7eef86f9f6eff5
BLAKE2b-256 checksum
How to use checksums
9a151b8370d87fd69529bf324b6b8be52ac88407e72d8714bfa97c7db03fc9b2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 3, 2025.

Transparency log

Security for coreagent 0.1.1a0

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for coreagent-0.1.1a0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 3, 2025.

Transparency log

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page