Lightning-AI/litAI

LLM router + minimal agent framework in one. Call any LLM API with OpenAI format. Unified billing, tools, retries, fallback, logging. Build agents and AI apps in pure Python. Full control. Zero magic.

59
/ 100
Established

This project helps AI application developers integrate and manage various large language models (LLMs) and build AI agents using standard Python code. It simplifies the process of sending prompts to different LLMs, handling tasks like retries, fallbacks, and unified billing. Developers input plain Python code with model calls and get back LLM responses, enabling them to create robust AI-powered features and applications.

Available on PyPI.

Use this if you are a Python developer building AI applications and need to interact with multiple LLMs efficiently, manage their usage, and construct AI agents with reliable tool use and control.

Not ideal if you are a non-technical end-user looking for a no-code solution or a ready-to-use AI application, as this project is a developer tool requiring Python coding skills.

AI-application-development LLM-integration AI-agent-building Python-development API-management
Maintenance 10 / 25
Adoption 8 / 25
Maturity 24 / 25
Community 17 / 25

How are scores calculated?

Stars

47

Forks

10

Language

Python

License

Apache-2.0

Last pushed

Jan 15, 2026

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Lightning-AI/litAI"

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