mpaepper/llm_agents

Build agents which are controlled by LLMs

54
/ 100
Established

This is a small library to help developers build AI agents that use large language models (LLMs) to automate multi-step tasks. Developers can define custom tools (like code execution or web search) and provide a prompt to guide the agent. The agent then processes information in a loop, interacting with these tools to arrive at a final answer. This is for developers looking to understand and build LLM-controlled agents with minimal code.

1,041 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a developer who wants to quickly understand and implement the core mechanics of an LLM-controlled agent from scratch.

Not ideal if you are looking for a high-level framework with extensive pre-built components and abstractions for building complex AI applications.

AI-development LLM-tooling agent-frameworks rapid-prototyping educational-coding
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

1,041

Forks

84

Language

Python

License

MIT

Last pushed

Jun 23, 2025

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mpaepper/llm_agents"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.