Python Agent Engine Agent Skill
by kennyzir
A production-ready Python AI Agent engine using LangChain. Supports ReAct pattern, tool calling, and thinking process tracking.
2k tokens
context cost
the whole folder, loaded on every use
3
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
311
stars on the repo
on the repository, not the skill itself
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/kennyzir/7deer_skills --skill python-agent-engineWhat comes with it
7 574 bytes besides the instructionresources/agent_engine.py
resources/requirements.txt
The instruction itself
4 sections, as written by the authorPython Agent Engine
A plug-and-play AI Agent core for Python applications. It handles the complexity of LLM interaction, tool calling loops, and context management.
Features
- ReAct Loop: Automatically handles "Reasoning -> Tool Call -> Result -> Answer" process.
- Thinking Process: Returns structured "Thinking Steps" for UI visualization.
- Model Agnostic: Works with OpenAI, DeepSeek, or any OpenAI-compatible API.
Installation
- Copy
resources/agent_engine.pyto your project (e.g.,src/core/agent_engine.py). - Install dependencies:
pip install langchain-core langchain-openai python-dotenv
- Set Environment Variables in your
.envfile:
OPENAI_API_KEY=sk-...
# Optional:
OPENAI_BASE_URL=https://api.openai.com/v1
Usage Example
import asyncio
from langchain_core.tools import tool
from core.agent_engine import AgentEngine
# 1. Define Tools
@tool
def calculator(expression: str) -> str:
"""Calculates a math expression."""
return str(eval(expression))
# 2. Initialize Agent
agent = AgentEngine(
tools=[calculator],
system_prompt="You are a helpful math assistant.",
model_name="gpt-4o"
)
# 3. Chat
async def main():
response = await agent.chat("What is 123 * 456?")
print(f"Answer: {response.content}")
print("\nThinking Steps:")
for step in response.thinking_steps:
print(f"[{step.type}] {step.content}")
if __name__ == "__main__":
asyncio.run(main())
How to use it
Copy the folder
Take kennyzir/python-agent-engine from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
Check the name does not clash
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
Install what it needs
The instructions reference pip.
Without those the skill loads but fails at the first command.